Model profile · DeepSeek

DeepSeek Reasoner

Open weightsbudget · registry tag 2026 open reasoning

Thin verified coverage

Reads as thin verified coverage across the resolved source data. Capability fit excludes speed and cost.

Visible coverage: 13%
Verified coverage: 13%
Spread: 62.9%
Last verified: Oct 3, 2026

48%capability fit

textcodedocument5 aliases29 official source links

Open compare

Data version

Current snapshot.

Published Oct 3, 2026Model list checked4 stale sources105 claim warnings9 providers · 1334 tracked models

The registry snapshot and page stamp are shown so a stale deploy is visible at a glance. View live data status.

Source-linked scores by benchmark

Each row keeps the benchmark source, source type, raw metric, and percentile inside its fair comparison set. Capability summaries exclude archived categories, speed, and cost; those rows remain below.

Thin verified coverageThis model currently reads as thin verified coverage across the resolved source data.

Chat / text24 benchmarks53.6%

Intelligence Index

AA · Chat / text · Combined

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #268 · Source label: DeepSeek R1 (Jan '25)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 11
Percentile: 51.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

51.9% percentile inside its fair comparison set

11Raw benchmark value

AA-Omniscience accuracy

AA · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #122 · Source label: DeepSeek R1 (Jan '25)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 30.5%
Percentile: 73.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

73.3% percentile inside its fair comparison set

30.5%Raw benchmark value

AA-Omniscience non-hallucination

AA · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #336 · Source label: DeepSeek R1 (Jan '25)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 9.7%
Percentile: 26%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

26% percentile inside its fair comparison set

9.7%Raw benchmark value

IFBench

AA · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #204 · Source label: DeepSeek R1 (Jan '25)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 39%
Percentile: 42%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `ifbench`.

42% percentile inside its fair comparison set

39%Raw benchmark value

Input price

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #264 · Source label: DeepSeek R1 (Jan '25)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $2 /1M input tokens
Percentile: 26.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

26.8% percentile inside its fair comparison set

$2 /1M input tokensRaw benchmark value

Output price

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #227 · Source label: DeepSeek R1 (Jan '25)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $4 /1M output tokens
Percentile: 36.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

36.4% percentile inside its fair comparison set

$4 /1M output tokensRaw benchmark value

Text Arena

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #145 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,398
Percentile: 61.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: overall. Source rank: #162. Votes: 18524. Organization: deepseek. License: MIT.

61.7% percentile inside its fair comparison set

1,398Raw benchmark valueCI 1,393 - 1,403

Text Arena · Creative Writing

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #130 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,374
Percentile: 65.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: creative_writing. Source rank: #148. Votes: 3289. Organization: deepseek. License: MIT.

65.5% percentile inside its fair comparison set

1,374Raw benchmark valueCI 1,364 - 1,384

Text Arena · English

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #144 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,413
Percentile: 62%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: english. Source rank: #160. Votes: 10721. Organization: deepseek. License: MIT.

62% percentile inside its fair comparison set

1,413Raw benchmark valueCI 1,407 - 1,419

Text Arena · Exclude Ties

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #142 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,383
Percentile: 62.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: exclude_ties. Source rank: #159. Votes: 12504. Organization: deepseek. License: MIT.

62.5% percentile inside its fair comparison set

1,383Raw benchmark valueCI 1,376 - 1,390

Text Arena · Hard Prompts

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #144 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,419
Percentile: 62%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: hard_prompts. Source rank: #161. Votes: 4116. Organization: deepseek. License: MIT.

62% percentile inside its fair comparison set

1,419Raw benchmark valueCI 1,410 - 1,428

Text Arena · Hard Prompts English

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #140 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,433
Percentile: 62.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: hard_prompts_english. Source rank: #155. Votes: 2656. Organization: deepseek. License: MIT.

62.8% percentile inside its fair comparison set

1,433Raw benchmark valueCI 1,421 - 1,444

Text Arena · Instruction Following

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #132 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,397
Percentile: 65.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: instruction_following. Source rank: #148. Votes: 6426. Organization: deepseek. License: MIT.

65.2% percentile inside its fair comparison set

1,397Raw benchmark valueCI 1,390 - 1,405

Text Arena · Longer Query

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #150 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,400
Percentile: 58%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: longer_query. Source rank: #170. Votes: 2303. Organization: deepseek. License: MIT.

58% percentile inside its fair comparison set

1,400Raw benchmark valueCI 1,388 - 1,412

Text Arena · Multi Turn

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #132 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,410
Percentile: 65%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: multi_turn. Source rank: #148. Votes: 2418. Organization: deepseek. License: MIT.

65% percentile inside its fair comparison set

1,410Raw benchmark valueCI 1,398 - 1,422

Text Arena · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #160 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,373
Percentile: 57.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: overall. Source rank: #178. Votes: 18524. Organization: deepseek. License: MIT.

57.7% percentile inside its fair comparison set

1,373Raw benchmark valueCI 1,368 - 1,378

Text Arena · Creative Writing · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #141 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,354
Percentile: 62.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: creative_writing. Source rank: #159. Votes: 3289. Organization: deepseek. License: MIT.

62.6% percentile inside its fair comparison set

1,354Raw benchmark valueCI 1,344 - 1,365

Text Arena · English · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #160 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,385
Percentile: 57.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: english. Source rank: #177. Votes: 10721. Organization: deepseek. License: MIT.

57.7% percentile inside its fair comparison set

1,385Raw benchmark valueCI 1,379 - 1,391

Text Arena · Exclude Ties · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #159 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,346
Percentile: 58%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: exclude_ties. Source rank: #176. Votes: 12504. Organization: deepseek. License: MIT.

58% percentile inside its fair comparison set

1,346Raw benchmark valueCI 1,339 - 1,353

Text Arena · Hard Prompts · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #176 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,361
Percentile: 53.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: hard_prompts. Source rank: #197. Votes: 4116. Organization: deepseek. License: MIT.

53.5% percentile inside its fair comparison set

1,361Raw benchmark valueCI 1,352 - 1,370

Text Arena · Hard Prompts English · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #175 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,375
Percentile: 53.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: hard_prompts_english. Source rank: #196. Votes: 2656. Organization: deepseek. License: MIT.

53.5% percentile inside its fair comparison set

1,375Raw benchmark valueCI 1,364 - 1,386

Text Arena · Instruction Following · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #157 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,358
Percentile: 58.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: instruction_following. Source rank: #175. Votes: 6426. Organization: deepseek. License: MIT.

58.5% percentile inside its fair comparison set

1,358Raw benchmark valueCI 1,350 - 1,365

Text Arena · Longer Query · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #168 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,355
Percentile: 53%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: longer_query. Source rank: #191. Votes: 2303. Organization: deepseek. License: MIT.

53% percentile inside its fair comparison set

1,355Raw benchmark valueCI 1,343 - 1,367

Text Arena · Multi Turn · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #144 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,390
Percentile: 61.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: multi_turn. Source rank: #160. Votes: 2418. Organization: deepseek. License: MIT.

61.8% percentile inside its fair comparison set

1,390Raw benchmark valueCI 1,379 - 1,402

Coding5 benchmarks32.4%

Terminal-Bench Hard

AA · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #195 · Source label: DeepSeek R1 (Jan '25)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 6.1%
Percentile: 41.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

41.9% percentile inside its fair comparison set

6.1%Raw benchmark value

SciCode

AA · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #155 · Source label: DeepSeek R1 (Jan '25)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 38.3%
Percentile: 22.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

22.2% percentile inside its fair comparison set

38.3%Raw benchmark value

Text Arena · Coding

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #144 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,444
Percentile: 61.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: coding. Source rank: #160. Votes: 2317. Organization: deepseek. License: MIT.

61.5% percentile inside its fair comparison set

1,444Raw benchmark valueCI 1,432 - 1,456

Text Arena · Coding · No Style Control

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #178 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,371
Percentile: 52.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: coding. Source rank: #199. Votes: 2317. Organization: deepseek. License: MIT.

52.3% percentile inside its fair comparison set

1,371Raw benchmark valueCI 1,360 - 1,383

LiveCodeBench

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #85 · Source label: fireworks/deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 70.2%
Percentile: 32.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: lcb; provider: Fireworks AI.

32.8% percentile inside its fair comparison set

70.2%Raw benchmark valueCI 68% - 72.5%

Reasoning / math / science6 benchmarks49.5%

Humanity's Last Exam

AA · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #259 · Source label: DeepSeek R1 (Jan '25)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 8.5%
Percentile: 51.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

51.2% percentile inside its fair comparison set

8.5%Raw benchmark value

GPQA

AA · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #220 · Source label: DeepSeek R1 (Jan '25)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 70.8%
Percentile: 55.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

55.6% percentile inside its fair comparison set

70.8%Raw benchmark value

CritPt

AA · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #176 · Source label: DeepSeek R1 (Jan '25)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 0.6%
Percentile: 62.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

62.8% percentile inside its fair comparison set

0.6%Raw benchmark value

Text Arena · Math

AR · Reasoning / math / science · Human

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #123 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,412
Percentile: 66%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: math. Source rank: #136. Votes: 1606. Organization: deepseek. License: MIT.

66% percentile inside its fair comparison set

1,412Raw benchmark valueCI 1,398 - 1,426

Text Arena · Math · No Style Control

AR · Reasoning / math / science · Human

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #151 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,392
Percentile: 58.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: math. Source rank: #166. Votes: 1606. Organization: deepseek. License: MIT.

58.2% percentile inside its fair comparison set

1,392Raw benchmark valueCI 1,378 - 1,406

MMLU Pro

VALS-AI · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #73 · Source label: fireworks/deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 83.2%
Percentile: 42.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: mmlu_pro; provider: Fireworks AI.

42.4% percentile inside its fair comparison set

83.2%Raw benchmark valueCI 82.3% - 84.1%

Professional reasoning20 benchmarks30.8%

Text Arena · Expert

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena expert leaderboard.

Rank #154 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,402
Percentile: 53.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: expert. Source rank: #172. Votes: 848. Organization: deepseek. License: MIT.

53.2% percentile inside its fair comparison set

1,402Raw benchmark valueCI 1,382 - 1,422

Text Arena · Industry Business And Management And Financial Operations

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_business_and_management_and_financial_operations leaderboard.

Rank #155 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,388
Percentile: 58.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: industry_business_and_management_and_financial_operations. Source rank: #173. Votes: 1798. Organization: deepseek. License: MIT.

58.3% percentile inside its fair comparison set

1,388Raw benchmark valueCI 1,374 - 1,402

Text Arena · Industry Entertainment And Sports And Media

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_entertainment_and_sports_and_media leaderboard.

Rank #134 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,372
Percentile: 64.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: industry_entertainment_and_sports_and_media. Source rank: #151. Votes: 3571. Organization: deepseek. License: MIT.

64.4% percentile inside its fair comparison set

1,372Raw benchmark valueCI 1,362 - 1,382

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_legal_and_government leaderboard.

Rank #152 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,399
Percentile: 56.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: industry_legal_and_government. Source rank: #170. Votes: 1097. Organization: deepseek. License: MIT.

56.7% percentile inside its fair comparison set

1,399Raw benchmark valueCI 1,381 - 1,417

Text Arena · Industry Life And Physical And Social Science

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_life_and_physical_and_social_science leaderboard.

Rank #149 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,411
Percentile: 60.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: industry_life_and_physical_and_social_science. Source rank: #166. Votes: 3309. Organization: deepseek. License: MIT.

60.4% percentile inside its fair comparison set

1,411Raw benchmark valueCI 1,401 - 1,421

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_mathematical leaderboard.

Rank #129 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,415
Percentile: 64%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: industry_mathematical. Source rank: #142. Votes: 1504. Organization: deepseek. License: MIT.

64% percentile inside its fair comparison set

1,415Raw benchmark valueCI 1,400 - 1,430

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_medicine_and_healthcare leaderboard.

Rank #151 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,413
Percentile: 56.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: industry_medicine_and_healthcare. Source rank: #169. Votes: 830. Organization: deepseek. License: MIT.

56.6% percentile inside its fair comparison set

1,413Raw benchmark valueCI 1,392 - 1,433

Text Arena · Industry Software And It Services

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_software_and_it_services leaderboard.

Rank #149 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,430
Percentile: 60.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: industry_software_and_it_services. Source rank: #164. Votes: 3954. Organization: deepseek. License: MIT.

60.6% percentile inside its fair comparison set

1,430Raw benchmark valueCI 1,421 - 1,439

Text Arena · Industry Writing And Literature And Language

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_writing_and_literature_and_language leaderboard.

Rank #134 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,382
Percentile: 64.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: industry_writing_and_literature_and_language. Source rank: #152. Votes: 5355. Organization: deepseek. License: MIT.

64.5% percentile inside its fair comparison set

1,382Raw benchmark valueCI 1,374 - 1,391

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena expert leaderboard.

Rank #185 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,337
Percentile: 43.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: expert. Source rank: #206. Votes: 848. Organization: deepseek. License: MIT.

43.7% percentile inside its fair comparison set

1,337Raw benchmark valueCI 1,318 - 1,357

Text Arena · Industry Business And Management And Financial Operations · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_business_and_management_and_financial_operations leaderboard.

Rank #173 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,347
Percentile: 53.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: industry_business_and_management_and_financial_operations. Source rank: #192. Votes: 1798. Organization: deepseek. License: MIT.

53.4% percentile inside its fair comparison set

1,347Raw benchmark valueCI 1,334 - 1,361

Text Arena · Industry Entertainment And Sports And Media · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_entertainment_and_sports_and_media leaderboard.

Rank #149 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,347
Percentile: 60.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: industry_entertainment_and_sports_and_media. Source rank: #167. Votes: 3571. Organization: deepseek. License: MIT.

60.4% percentile inside its fair comparison set

1,347Raw benchmark valueCI 1,337 - 1,357

Text Arena · Industry Legal And Government · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_legal_and_government leaderboard.

Rank #165 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,371
Percentile: 53%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: industry_legal_and_government. Source rank: #185. Votes: 1097. Organization: deepseek. License: MIT.

53% percentile inside its fair comparison set

1,371Raw benchmark valueCI 1,353 - 1,388

Text Arena · Industry Life And Physical And Social Science · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_life_and_physical_and_social_science leaderboard.

Rank #169 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,375
Percentile: 55.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: industry_life_and_physical_and_social_science. Source rank: #186. Votes: 3309. Organization: deepseek. License: MIT.

55.1% percentile inside its fair comparison set

1,375Raw benchmark valueCI 1,365 - 1,385

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_mathematical leaderboard.

Rank #155 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,389
Percentile: 56.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: industry_mathematical. Source rank: #170. Votes: 1504. Organization: deepseek. License: MIT.

56.7% percentile inside its fair comparison set

1,389Raw benchmark valueCI 1,375 - 1,404

Text Arena · Industry Medicine And Healthcare · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_medicine_and_healthcare leaderboard.

Rank #163 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,370
Percentile: 53.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: industry_medicine_and_healthcare. Source rank: #182. Votes: 830. Organization: deepseek. License: MIT.

53.2% percentile inside its fair comparison set

1,370Raw benchmark valueCI 1,350 - 1,391

Text Arena · Industry Software And It Services · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_software_and_it_services leaderboard.

Rank #178 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,375
Percentile: 52.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: industry_software_and_it_services. Source rank: #198. Votes: 3954. Organization: deepseek. License: MIT.

52.9% percentile inside its fair comparison set

1,375Raw benchmark valueCI 1,366 - 1,384

Text Arena · Industry Writing And Literature And Language · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_writing_and_literature_and_language leaderboard.

Rank #147 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,365
Percentile: 61.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: industry_writing_and_literature_and_language. Source rank: #165. Votes: 5355. Organization: deepseek. License: MIT.

61.1% percentile inside its fair comparison set

1,365Raw benchmark valueCI 1,356 - 1,373

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #122 · Source label: fireworks/deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 67.3%
Percentile: 10.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: legal_bench; provider: Fireworks AI.

10.4% percentile inside its fair comparison set

67.3%Raw benchmark valueCI 66.3% - 68.4%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #64 · Source label: fireworks/deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 72.3%
Percentile: 51.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Fireworks AI.

51.2% percentile inside its fair comparison set

72.3%Raw benchmark valueCI 70.6% - 74%

Search / tool use1 benchmark11.5%

Tau2-Bench Telecom

AA · Search / tool use · Objective

It matters when the model must browse, call tools, and recover useful answers from external systems.

Rank #301 · Source label: DeepSeek R1 (Jan '25)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 11.4%
Percentile: 11.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `tau2`.

11.5% percentile inside its fair comparison set

11.4%Raw benchmark value

Long context2 benchmarks39.9%

Long Context Reasoning

AA · Long context · Objective

It checks whether long-context claims survive contact with retrieval, memory, or long-document tasks.

Rank #206 · Source label: DeepSeek R1 (Jan '25)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 57.7%
Percentile: 54.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

54.9% percentile inside its fair comparison set

57.7%Raw benchmark value

CorpFin v2

VALS-AI · Long context · Objective

It checks whether long-context claims survive contact with retrieval, memory, or long-document tasks.

Rank #89 · Source label: fireworks/deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 54.1%
Percentile: 24.8%
Last updated: aging
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: corp_fin_v2; provider: Fireworks AI.

24.8% percentile inside its fair comparison set

54.1%Raw benchmark valueCI 52.2% - 56%

Multilingual16 benchmarksn/a

Text Arena · Chinese

AR · Multilingual · Human

Observed user preference in Arena's Text Arena chinese leaderboard.

Rank #143 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,428
Percentile: 59.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: chinese. Source rank: #160. Votes: 1151. Organization: deepseek. License: MIT.

59.7% percentile inside its fair comparison set

1,428Raw benchmark valueCI 1,410 - 1,447

Text Arena · French

AR · Multilingual · Human

Observed user preference in Arena's Text Arena french leaderboard.

Rank #151 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,390
Percentile: 41.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: french. Source rank: #170. Votes: 188. Organization: deepseek. License: MIT.

41.6% percentile inside its fair comparison set

1,390Raw benchmark valueCI 1,348 - 1,431

Text Arena · German

AR · Multilingual · Human

Observed user preference in Arena's Text Arena german leaderboard.

Rank #107 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,399
Percentile: 61%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: german. Source rank: #123. Votes: 436. Organization: deepseek. License: MIT.

61% percentile inside its fair comparison set

1,399Raw benchmark valueCI 1,371 - 1,428

Text Arena · Japanese

AR · Multilingual · Human

Observed user preference in Arena's Text Arena japanese leaderboard.

Rank #118 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,337
Percentile: 51.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: japanese. Source rank: #136. Votes: 468. Organization: deepseek. License: MIT.

51.9% percentile inside its fair comparison set

1,337Raw benchmark valueCI 1,311 - 1,363

Text Arena · Korean

AR · Multilingual · Human

Observed user preference in Arena's Text Arena korean leaderboard.

Rank #106 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,358
Percentile: 57%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: korean. Source rank: #122. Votes: 215. Organization: deepseek. License: MIT.

57% percentile inside its fair comparison set

1,358Raw benchmark valueCI 1,318 - 1,398

Text Arena · Non English

AR · Multilingual · Human

Observed user preference in Arena's Text Arena non_english leaderboard.

Rank #149 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,378
Percentile: 60.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: non_english. Source rank: #168. Votes: 7803. Organization: deepseek. License: MIT.

60.6% percentile inside its fair comparison set

1,378Raw benchmark valueCI 1,371 - 1,385

Text Arena · Russian

AR · Multilingual · Human

Observed user preference in Arena's Text Arena russian leaderboard.

Rank #150 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,382
Percentile: 56.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: russian. Source rank: #168. Votes: 1904. Organization: deepseek. License: MIT.

56.3% percentile inside its fair comparison set

1,382Raw benchmark valueCI 1,369 - 1,395

Text Arena · Spanish

AR · Multilingual · Human

Observed user preference in Arena's Text Arena spanish leaderboard.

Rank #128 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,399
Percentile: 51%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: spanish. Source rank: #145. Votes: 114. Organization: deepseek. License: MIT.

51% percentile inside its fair comparison set

1,399Raw benchmark valueCI 1,347 - 1,451

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena chinese leaderboard.

Rank #160 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,400
Percentile: 54.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: chinese. Source rank: #178. Votes: 1151. Organization: deepseek. License: MIT.

54.8% percentile inside its fair comparison set

1,400Raw benchmark valueCI 1,382 - 1,418

Text Arena · French · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena french leaderboard.

Rank #152 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,365
Percentile: 41.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: french. Source rank: #169. Votes: 188. Organization: deepseek. License: MIT.

41.2% percentile inside its fair comparison set

1,365Raw benchmark valueCI 1,323 - 1,408

Text Arena · German · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena german leaderboard.

Rank #118 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,384
Percentile: 57%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: german. Source rank: #132. Votes: 436. Organization: deepseek. License: MIT.

57% percentile inside its fair comparison set

1,384Raw benchmark valueCI 1,356 - 1,413

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena japanese leaderboard.

Rank #121 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,324
Percentile: 50.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: japanese. Source rank: #138. Votes: 468. Organization: deepseek. License: MIT.

50.6% percentile inside its fair comparison set

1,324Raw benchmark valueCI 1,298 - 1,350

Text Arena · Korean · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena korean leaderboard.

Rank #129 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,329
Percentile: 47.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: korean. Source rank: #146. Votes: 215. Organization: deepseek. License: MIT.

47.5% percentile inside its fair comparison set

1,329Raw benchmark valueCI 1,290 - 1,369

Text Arena · Non English · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena non_english leaderboard.

Rank #162 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,357
Percentile: 57.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: non_english. Source rank: #181. Votes: 7803. Organization: deepseek. License: MIT.

57.2% percentile inside its fair comparison set

1,357Raw benchmark valueCI 1,350 - 1,363

Text Arena · Russian · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena russian leaderboard.

Rank #164 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,354
Percentile: 52.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: russian. Source rank: #184. Votes: 1904. Organization: deepseek. License: MIT.

52.2% percentile inside its fair comparison set

1,354Raw benchmark valueCI 1,341 - 1,367

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena spanish leaderboard.

Rank #145 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,379
Percentile: 44.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: spanish. Source rank: #161. Votes: 114. Organization: deepseek. License: MIT.

44.4% percentile inside its fair comparison set

1,379Raw benchmark valueCI 1,326 - 1,432

Source links and registry checks

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Artificial Analysis

Oct 3, 2026

source →

Model profile · DeepSeek

DeepSeek Reasoner

Open weightsbudget · registry tag 2026 open reasoning

Thin verified coverage

Reads as thin verified coverage across the resolved source data. Capability fit excludes speed and cost.

Visible coverage: 13%
Verified coverage: 13%
Spread: 62.9%
Last verified: Oct 3, 2026

48%capability fit

textcodedocument5 aliases29 official source links

Open compare

Data version

Current snapshot.

Published Oct 3, 2026Model list checked4 stale sources105 claim warnings9 providers · 1334 tracked models

The registry snapshot and page stamp are shown so a stale deploy is visible at a glance. View live data status.

Source-linked scores by benchmark

Thin verified coverageThis model currently reads as thin verified coverage across the resolved source data.

Chat / text24 benchmarks53.6%

Intelligence Index

AA · Chat / text · Combined

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #268 · Source label: DeepSeek R1 (Jan '25)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 11
Percentile: 51.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

51.9% percentile inside its fair comparison set

11Raw benchmark value

AA-Omniscience accuracy

AA · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #122 · Source label: DeepSeek R1 (Jan '25)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 30.5%
Percentile: 73.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

73.3% percentile inside its fair comparison set

30.5%Raw benchmark value

AA-Omniscience non-hallucination

AA · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #336 · Source label: DeepSeek R1 (Jan '25)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 9.7%
Percentile: 26%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

26% percentile inside its fair comparison set

9.7%Raw benchmark value

IFBench

AA · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #204 · Source label: DeepSeek R1 (Jan '25)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 39%
Percentile: 42%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `ifbench`.

42% percentile inside its fair comparison set

39%Raw benchmark value

Input price

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #264 · Source label: DeepSeek R1 (Jan '25)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $2 /1M input tokens
Percentile: 26.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

26.8% percentile inside its fair comparison set

$2 /1M input tokensRaw benchmark value

Output price

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #227 · Source label: DeepSeek R1 (Jan '25)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $4 /1M output tokens
Percentile: 36.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

36.4% percentile inside its fair comparison set

$4 /1M output tokensRaw benchmark value

Text Arena

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #145 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,398
Percentile: 61.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: overall. Source rank: #162. Votes: 18524. Organization: deepseek. License: MIT.

61.7% percentile inside its fair comparison set

1,398Raw benchmark valueCI 1,393 - 1,403

Text Arena · Creative Writing

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #130 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,374
Percentile: 65.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: creative_writing. Source rank: #148. Votes: 3289. Organization: deepseek. License: MIT.

65.5% percentile inside its fair comparison set

1,374Raw benchmark valueCI 1,364 - 1,384

Text Arena · English

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #144 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,413
Percentile: 62%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: english. Source rank: #160. Votes: 10721. Organization: deepseek. License: MIT.

62% percentile inside its fair comparison set

1,413Raw benchmark valueCI 1,407 - 1,419

Text Arena · Exclude Ties

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #142 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,383
Percentile: 62.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: exclude_ties. Source rank: #159. Votes: 12504. Organization: deepseek. License: MIT.

62.5% percentile inside its fair comparison set

1,383Raw benchmark valueCI 1,376 - 1,390

Text Arena · Hard Prompts

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #144 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,419
Percentile: 62%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: hard_prompts. Source rank: #161. Votes: 4116. Organization: deepseek. License: MIT.

62% percentile inside its fair comparison set

1,419Raw benchmark valueCI 1,410 - 1,428

Text Arena · Hard Prompts English

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #140 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,433
Percentile: 62.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: hard_prompts_english. Source rank: #155. Votes: 2656. Organization: deepseek. License: MIT.

62.8% percentile inside its fair comparison set

1,433Raw benchmark valueCI 1,421 - 1,444

Text Arena · Instruction Following

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #132 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,397
Percentile: 65.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: instruction_following. Source rank: #148. Votes: 6426. Organization: deepseek. License: MIT.

65.2% percentile inside its fair comparison set

1,397Raw benchmark valueCI 1,390 - 1,405

Text Arena · Longer Query

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #150 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,400
Percentile: 58%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: longer_query. Source rank: #170. Votes: 2303. Organization: deepseek. License: MIT.

58% percentile inside its fair comparison set

1,400Raw benchmark valueCI 1,388 - 1,412

Text Arena · Multi Turn

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #132 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,410
Percentile: 65%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: multi_turn. Source rank: #148. Votes: 2418. Organization: deepseek. License: MIT.

65% percentile inside its fair comparison set

1,410Raw benchmark valueCI 1,398 - 1,422

Text Arena · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #160 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,373
Percentile: 57.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: overall. Source rank: #178. Votes: 18524. Organization: deepseek. License: MIT.

57.7% percentile inside its fair comparison set

1,373Raw benchmark valueCI 1,368 - 1,378

Text Arena · Creative Writing · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #141 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,354
Percentile: 62.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: creative_writing. Source rank: #159. Votes: 3289. Organization: deepseek. License: MIT.

62.6% percentile inside its fair comparison set

1,354Raw benchmark valueCI 1,344 - 1,365

Text Arena · English · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #160 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,385
Percentile: 57.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: english. Source rank: #177. Votes: 10721. Organization: deepseek. License: MIT.

57.7% percentile inside its fair comparison set

1,385Raw benchmark valueCI 1,379 - 1,391

Text Arena · Exclude Ties · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #159 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,346
Percentile: 58%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: exclude_ties. Source rank: #176. Votes: 12504. Organization: deepseek. License: MIT.

58% percentile inside its fair comparison set

1,346Raw benchmark valueCI 1,339 - 1,353

Text Arena · Hard Prompts · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #176 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,361
Percentile: 53.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: hard_prompts. Source rank: #197. Votes: 4116. Organization: deepseek. License: MIT.

53.5% percentile inside its fair comparison set

1,361Raw benchmark valueCI 1,352 - 1,370

Text Arena · Hard Prompts English · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #175 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,375
Percentile: 53.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: hard_prompts_english. Source rank: #196. Votes: 2656. Organization: deepseek. License: MIT.

53.5% percentile inside its fair comparison set

1,375Raw benchmark valueCI 1,364 - 1,386

Text Arena · Instruction Following · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #157 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,358
Percentile: 58.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: instruction_following. Source rank: #175. Votes: 6426. Organization: deepseek. License: MIT.

58.5% percentile inside its fair comparison set

1,358Raw benchmark valueCI 1,350 - 1,365

Text Arena · Longer Query · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #168 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,355
Percentile: 53%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: longer_query. Source rank: #191. Votes: 2303. Organization: deepseek. License: MIT.

53% percentile inside its fair comparison set

1,355Raw benchmark valueCI 1,343 - 1,367

Text Arena · Multi Turn · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #144 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,390
Percentile: 61.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: multi_turn. Source rank: #160. Votes: 2418. Organization: deepseek. License: MIT.

61.8% percentile inside its fair comparison set

1,390Raw benchmark valueCI 1,379 - 1,402

Coding5 benchmarks32.4%

Terminal-Bench Hard

AA · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #195 · Source label: DeepSeek R1 (Jan '25)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 6.1%
Percentile: 41.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `terminalbenchHard`.

41.9% percentile inside its fair comparison set

6.1%Raw benchmark value

SciCode

AA · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #155 · Source label: DeepSeek R1 (Jan '25)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 38.3%
Percentile: 22.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

22.2% percentile inside its fair comparison set

38.3%Raw benchmark value

Text Arena · Coding

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #144 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,444
Percentile: 61.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: coding. Source rank: #160. Votes: 2317. Organization: deepseek. License: MIT.

61.5% percentile inside its fair comparison set

1,444Raw benchmark valueCI 1,432 - 1,456

Text Arena · Coding · No Style Control

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #178 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,371
Percentile: 52.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: coding. Source rank: #199. Votes: 2317. Organization: deepseek. License: MIT.

52.3% percentile inside its fair comparison set

1,371Raw benchmark valueCI 1,360 - 1,383

LiveCodeBench

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #85 · Source label: fireworks/deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 70.2%
Percentile: 32.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: lcb; provider: Fireworks AI.

32.8% percentile inside its fair comparison set

70.2%Raw benchmark valueCI 68% - 72.5%

Reasoning / math / science6 benchmarks49.5%

Humanity's Last Exam

AA · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #259 · Source label: DeepSeek R1 (Jan '25)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 8.5%
Percentile: 51.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

51.2% percentile inside its fair comparison set

8.5%Raw benchmark value

GPQA

AA · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #220 · Source label: DeepSeek R1 (Jan '25)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 70.8%
Percentile: 55.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

55.6% percentile inside its fair comparison set

70.8%Raw benchmark value

CritPt

AA · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #176 · Source label: DeepSeek R1 (Jan '25)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 0.6%
Percentile: 62.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

62.8% percentile inside its fair comparison set

0.6%Raw benchmark value

Text Arena · Math

AR · Reasoning / math / science · Human

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #123 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,412
Percentile: 66%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: math. Source rank: #136. Votes: 1606. Organization: deepseek. License: MIT.

66% percentile inside its fair comparison set

1,412Raw benchmark valueCI 1,398 - 1,426

Text Arena · Math · No Style Control

AR · Reasoning / math / science · Human

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #151 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,392
Percentile: 58.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: math. Source rank: #166. Votes: 1606. Organization: deepseek. License: MIT.

58.2% percentile inside its fair comparison set

1,392Raw benchmark valueCI 1,378 - 1,406

MMLU Pro

VALS-AI · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #73 · Source label: fireworks/deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 83.2%
Percentile: 42.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: mmlu_pro; provider: Fireworks AI.

42.4% percentile inside its fair comparison set

83.2%Raw benchmark valueCI 82.3% - 84.1%

Professional reasoning20 benchmarks30.8%

Text Arena · Expert

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena expert leaderboard.

Rank #154 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,402
Percentile: 53.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: expert. Source rank: #172. Votes: 848. Organization: deepseek. License: MIT.

53.2% percentile inside its fair comparison set

1,402Raw benchmark valueCI 1,382 - 1,422

Text Arena · Industry Business And Management And Financial Operations

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_business_and_management_and_financial_operations leaderboard.

Rank #155 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,388
Percentile: 58.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: industry_business_and_management_and_financial_operations. Source rank: #173. Votes: 1798. Organization: deepseek. License: MIT.

58.3% percentile inside its fair comparison set

1,388Raw benchmark valueCI 1,374 - 1,402

Text Arena · Industry Entertainment And Sports And Media

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_entertainment_and_sports_and_media leaderboard.

Rank #134 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,372
Percentile: 64.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: industry_entertainment_and_sports_and_media. Source rank: #151. Votes: 3571. Organization: deepseek. License: MIT.

64.4% percentile inside its fair comparison set

1,372Raw benchmark valueCI 1,362 - 1,382

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_legal_and_government leaderboard.

Rank #152 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,399
Percentile: 56.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: industry_legal_and_government. Source rank: #170. Votes: 1097. Organization: deepseek. License: MIT.

56.7% percentile inside its fair comparison set

1,399Raw benchmark valueCI 1,381 - 1,417

Text Arena · Industry Life And Physical And Social Science

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_life_and_physical_and_social_science leaderboard.

Rank #149 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,411
Percentile: 60.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: industry_life_and_physical_and_social_science. Source rank: #166. Votes: 3309. Organization: deepseek. License: MIT.

60.4% percentile inside its fair comparison set

1,411Raw benchmark valueCI 1,401 - 1,421

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_mathematical leaderboard.

Rank #129 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,415
Percentile: 64%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: industry_mathematical. Source rank: #142. Votes: 1504. Organization: deepseek. License: MIT.

64% percentile inside its fair comparison set

1,415Raw benchmark valueCI 1,400 - 1,430

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_medicine_and_healthcare leaderboard.

Rank #151 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,413
Percentile: 56.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: industry_medicine_and_healthcare. Source rank: #169. Votes: 830. Organization: deepseek. License: MIT.

56.6% percentile inside its fair comparison set

1,413Raw benchmark valueCI 1,392 - 1,433

Text Arena · Industry Software And It Services

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_software_and_it_services leaderboard.

Rank #149 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,430
Percentile: 60.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: industry_software_and_it_services. Source rank: #164. Votes: 3954. Organization: deepseek. License: MIT.

60.6% percentile inside its fair comparison set

1,430Raw benchmark valueCI 1,421 - 1,439

Text Arena · Industry Writing And Literature And Language

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_writing_and_literature_and_language leaderboard.

Rank #134 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,382
Percentile: 64.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: industry_writing_and_literature_and_language. Source rank: #152. Votes: 5355. Organization: deepseek. License: MIT.

64.5% percentile inside its fair comparison set

1,382Raw benchmark valueCI 1,374 - 1,391

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena expert leaderboard.

Rank #185 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,337
Percentile: 43.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: expert. Source rank: #206. Votes: 848. Organization: deepseek. License: MIT.

43.7% percentile inside its fair comparison set

1,337Raw benchmark valueCI 1,318 - 1,357

Text Arena · Industry Business And Management And Financial Operations · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_business_and_management_and_financial_operations leaderboard.

Rank #173 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,347
Percentile: 53.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: industry_business_and_management_and_financial_operations. Source rank: #192. Votes: 1798. Organization: deepseek. License: MIT.

53.4% percentile inside its fair comparison set

1,347Raw benchmark valueCI 1,334 - 1,361

Text Arena · Industry Entertainment And Sports And Media · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_entertainment_and_sports_and_media leaderboard.

Rank #149 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,347
Percentile: 60.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: industry_entertainment_and_sports_and_media. Source rank: #167. Votes: 3571. Organization: deepseek. License: MIT.

60.4% percentile inside its fair comparison set

1,347Raw benchmark valueCI 1,337 - 1,357

Text Arena · Industry Legal And Government · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_legal_and_government leaderboard.

Rank #165 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,371
Percentile: 53%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: industry_legal_and_government. Source rank: #185. Votes: 1097. Organization: deepseek. License: MIT.

53% percentile inside its fair comparison set

1,371Raw benchmark valueCI 1,353 - 1,388

Text Arena · Industry Life And Physical And Social Science · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_life_and_physical_and_social_science leaderboard.

Rank #169 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,375
Percentile: 55.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: industry_life_and_physical_and_social_science. Source rank: #186. Votes: 3309. Organization: deepseek. License: MIT.

55.1% percentile inside its fair comparison set

1,375Raw benchmark valueCI 1,365 - 1,385

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_mathematical leaderboard.

Rank #155 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,389
Percentile: 56.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: industry_mathematical. Source rank: #170. Votes: 1504. Organization: deepseek. License: MIT.

56.7% percentile inside its fair comparison set

1,389Raw benchmark valueCI 1,375 - 1,404

Text Arena · Industry Medicine And Healthcare · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_medicine_and_healthcare leaderboard.

Rank #163 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,370
Percentile: 53.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: industry_medicine_and_healthcare. Source rank: #182. Votes: 830. Organization: deepseek. License: MIT.

53.2% percentile inside its fair comparison set

1,370Raw benchmark valueCI 1,350 - 1,391

Text Arena · Industry Software And It Services · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_software_and_it_services leaderboard.

Rank #178 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,375
Percentile: 52.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: industry_software_and_it_services. Source rank: #198. Votes: 3954. Organization: deepseek. License: MIT.

52.9% percentile inside its fair comparison set

1,375Raw benchmark valueCI 1,366 - 1,384

Text Arena · Industry Writing And Literature And Language · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_writing_and_literature_and_language leaderboard.

Rank #147 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,365
Percentile: 61.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: industry_writing_and_literature_and_language. Source rank: #165. Votes: 5355. Organization: deepseek. License: MIT.

61.1% percentile inside its fair comparison set

1,365Raw benchmark valueCI 1,356 - 1,373

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #122 · Source label: fireworks/deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 67.3%
Percentile: 10.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: legal_bench; provider: Fireworks AI.

10.4% percentile inside its fair comparison set

67.3%Raw benchmark valueCI 66.3% - 68.4%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #64 · Source label: fireworks/deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 72.3%
Percentile: 51.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Fireworks AI.

51.2% percentile inside its fair comparison set

72.3%Raw benchmark valueCI 70.6% - 74%

Search / tool use1 benchmark11.5%

Tau2-Bench Telecom

AA · Search / tool use · Objective

It matters when the model must browse, call tools, and recover useful answers from external systems.

Rank #301 · Source label: DeepSeek R1 (Jan '25)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 11.4%
Percentile: 11.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `tau2`.

11.5% percentile inside its fair comparison set

11.4%Raw benchmark value

Long context2 benchmarks39.9%

Long Context Reasoning

AA · Long context · Objective

It checks whether long-context claims survive contact with retrieval, memory, or long-document tasks.

Rank #206 · Source label: DeepSeek R1 (Jan '25)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 57.7%
Percentile: 54.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

54.9% percentile inside its fair comparison set

57.7%Raw benchmark value

CorpFin v2

VALS-AI · Long context · Objective

It checks whether long-context claims survive contact with retrieval, memory, or long-document tasks.

Rank #89 · Source label: fireworks/deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 54.1%
Percentile: 24.8%
Last updated: aging
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: corp_fin_v2; provider: Fireworks AI.

24.8% percentile inside its fair comparison set

54.1%Raw benchmark valueCI 52.2% - 56%

Multilingual16 benchmarksn/a

Text Arena · Chinese

AR · Multilingual · Human

Observed user preference in Arena's Text Arena chinese leaderboard.

Rank #143 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,428
Percentile: 59.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: chinese. Source rank: #160. Votes: 1151. Organization: deepseek. License: MIT.

59.7% percentile inside its fair comparison set

1,428Raw benchmark valueCI 1,410 - 1,447

Text Arena · French

AR · Multilingual · Human

Observed user preference in Arena's Text Arena french leaderboard.

Rank #151 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,390
Percentile: 41.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: french. Source rank: #170. Votes: 188. Organization: deepseek. License: MIT.

41.6% percentile inside its fair comparison set

1,390Raw benchmark valueCI 1,348 - 1,431

Text Arena · German

AR · Multilingual · Human

Observed user preference in Arena's Text Arena german leaderboard.

Rank #107 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,399
Percentile: 61%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: german. Source rank: #123. Votes: 436. Organization: deepseek. License: MIT.

61% percentile inside its fair comparison set

1,399Raw benchmark valueCI 1,371 - 1,428

Text Arena · Japanese

AR · Multilingual · Human

Observed user preference in Arena's Text Arena japanese leaderboard.

Rank #118 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,337
Percentile: 51.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: japanese. Source rank: #136. Votes: 468. Organization: deepseek. License: MIT.

51.9% percentile inside its fair comparison set

1,337Raw benchmark valueCI 1,311 - 1,363

Text Arena · Korean

AR · Multilingual · Human

Observed user preference in Arena's Text Arena korean leaderboard.

Rank #106 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,358
Percentile: 57%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: korean. Source rank: #122. Votes: 215. Organization: deepseek. License: MIT.

57% percentile inside its fair comparison set

1,358Raw benchmark valueCI 1,318 - 1,398

Text Arena · Non English

AR · Multilingual · Human

Observed user preference in Arena's Text Arena non_english leaderboard.

Rank #149 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,378
Percentile: 60.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: non_english. Source rank: #168. Votes: 7803. Organization: deepseek. License: MIT.

60.6% percentile inside its fair comparison set

1,378Raw benchmark valueCI 1,371 - 1,385

Text Arena · Russian

AR · Multilingual · Human

Observed user preference in Arena's Text Arena russian leaderboard.

Rank #150 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,382
Percentile: 56.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: russian. Source rank: #168. Votes: 1904. Organization: deepseek. License: MIT.

56.3% percentile inside its fair comparison set

1,382Raw benchmark valueCI 1,369 - 1,395

Text Arena · Spanish

AR · Multilingual · Human

Observed user preference in Arena's Text Arena spanish leaderboard.

Rank #128 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,399
Percentile: 51%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: spanish. Source rank: #145. Votes: 114. Organization: deepseek. License: MIT.

51% percentile inside its fair comparison set

1,399Raw benchmark valueCI 1,347 - 1,451

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena chinese leaderboard.

Rank #160 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,400
Percentile: 54.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: chinese. Source rank: #178. Votes: 1151. Organization: deepseek. License: MIT.

54.8% percentile inside its fair comparison set

1,400Raw benchmark valueCI 1,382 - 1,418

Text Arena · French · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena french leaderboard.

Rank #152 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,365
Percentile: 41.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: french. Source rank: #169. Votes: 188. Organization: deepseek. License: MIT.

41.2% percentile inside its fair comparison set

1,365Raw benchmark valueCI 1,323 - 1,408

Text Arena · German · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena german leaderboard.

Rank #118 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,384
Percentile: 57%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: german. Source rank: #132. Votes: 436. Organization: deepseek. License: MIT.

57% percentile inside its fair comparison set

1,384Raw benchmark valueCI 1,356 - 1,413

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena japanese leaderboard.

Rank #121 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,324
Percentile: 50.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: japanese. Source rank: #138. Votes: 468. Organization: deepseek. License: MIT.

50.6% percentile inside its fair comparison set

1,324Raw benchmark valueCI 1,298 - 1,350

Text Arena · Korean · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena korean leaderboard.

Rank #129 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,329
Percentile: 47.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: korean. Source rank: #146. Votes: 215. Organization: deepseek. License: MIT.

47.5% percentile inside its fair comparison set

1,329Raw benchmark valueCI 1,290 - 1,369

Text Arena · Non English · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena non_english leaderboard.

Rank #162 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,357
Percentile: 57.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: non_english. Source rank: #181. Votes: 7803. Organization: deepseek. License: MIT.

57.2% percentile inside its fair comparison set

1,357Raw benchmark valueCI 1,350 - 1,363

Text Arena · Russian · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena russian leaderboard.

Rank #164 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,354
Percentile: 52.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: russian. Source rank: #184. Votes: 1904. Organization: deepseek. License: MIT.

52.2% percentile inside its fair comparison set

1,354Raw benchmark valueCI 1,341 - 1,367

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena spanish leaderboard.

Rank #145 · Source label: deepseek-r1

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,379
Percentile: 44.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `deepseek-r1`. Category: spanish. Source rank: #161. Votes: 114. Organization: deepseek. License: MIT.

44.4% percentile inside its fair comparison set

1,379Raw benchmark valueCI 1,326 - 1,432

Source links and registry checks

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Artificial Analysis

Oct 3, 2026

source →

DeepSeek Reasoner

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks

Loading model evidence.

DeepSeek Reasoner

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks