Model profile · Unknown

kimi-k2.5-instant

Unknown weightsmid · registry tag 2026 benchmark-derived

Thin verified coverage

Reads as thin verified coverage across the resolved source data.

Visible coverage: 2.7%
Verified coverage: 2.7%
Spread: n/a
Last verified: Jun 20, 2026

textcodevision2 aliases38 official source links

Open compare

Data version

Current snapshot.

Data version Jun 20, 2026Model list checked9 providers · 1081 tracked modelsPage refreshed Jul 5, 2026

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

Source-linked scores by benchmark

Each row keeps the benchmark source, source type, raw metric, and percentile inside its fair comparison set.

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

Chat / text18 benchmarks83.8%

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 #56 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,431
Percentile: 83.1%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: overall. Source rank: #72. Votes: 8177. Organization: moonshot. License: Modified MIT.

83.1% percentile inside its fair comparison set

1,431Raw benchmark valueCI 1,425 - 1,438

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 #76 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,390
Percentile: 76.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: creative_writing. Source rank: #93. Votes: 1271. Organization: moonshot. License: Modified MIT.

76.8% percentile inside its fair comparison set

1,390Raw benchmark valueCI 1,373 - 1,406

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 #53 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,445
Percentile: 84%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: english. Source rank: #65. Votes: 3712. Organization: moonshot. License: Modified MIT.

84% percentile inside its fair comparison set

1,445Raw benchmark valueCI 1,435 - 1,454

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 #55 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,426
Percentile: 83.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: exclude_ties. Source rank: #71. Votes: 5644. Organization: moonshot. License: Modified MIT.

83.4% percentile inside its fair comparison set

1,426Raw benchmark valueCI 1,416 - 1,435

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 #46 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,461
Percentile: 86.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: hard_prompts. Source rank: #58. Votes: 4535. Organization: moonshot. License: Modified MIT.

86.2% percentile inside its fair comparison set

1,461Raw benchmark valueCI 1,452 - 1,469

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 #48 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,465
Percentile: 85.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: hard_prompts_english. Source rank: #60. Votes: 2147. Organization: moonshot. License: Modified MIT.

85.5% percentile inside its fair comparison set

1,465Raw benchmark valueCI 1,452 - 1,477

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 #41 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,435
Percentile: 87.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: instruction_following. Source rank: #52. Votes: 2232. Organization: moonshot. License: Modified MIT.

87.7% percentile inside its fair comparison set

1,435Raw benchmark valueCI 1,422 - 1,447

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 #51 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,445
Percentile: 83.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: longer_query. Source rank: #64. Votes: 2211. Organization: moonshot. License: Modified MIT.

83.6% percentile inside its fair comparison set

1,445Raw benchmark valueCI 1,433 - 1,458

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 #53 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,439
Percentile: 83.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: multi_turn. Source rank: #70. Votes: 1467. Organization: moonshot. License: Modified MIT.

83.9% percentile inside its fair comparison set

1,439Raw benchmark valueCI 1,424 - 1,454

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 #62 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,420
Percentile: 81.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: overall. Source rank: #75. Votes: 8177. Organization: moonshot. License: Modified MIT.

81.2% percentile inside its fair comparison set

1,420Raw benchmark valueCI 1,414 - 1,427

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 #77 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,380
Percentile: 76.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: creative_writing. Source rank: #93. Votes: 1271. Organization: moonshot. License: Modified MIT.

76.5% percentile inside its fair comparison set

1,380Raw benchmark valueCI 1,363 - 1,396

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 #61 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,433
Percentile: 81.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: english. Source rank: #73. Votes: 3712. Organization: moonshot. License: Modified MIT.

81.5% percentile inside its fair comparison set

1,433Raw benchmark valueCI 1,423 - 1,442

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 #65 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,409
Percentile: 80.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: exclude_ties. Source rank: #78. Votes: 5644. Organization: moonshot. License: Modified MIT.

80.3% percentile inside its fair comparison set

1,409Raw benchmark valueCI 1,400 - 1,418

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 #42 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,444
Percentile: 87.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: hard_prompts. Source rank: #50. Votes: 4535. Organization: moonshot. License: Modified MIT.

87.4% percentile inside its fair comparison set

1,444Raw benchmark valueCI 1,435 - 1,452

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 #42 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,449
Percentile: 87.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: hard_prompts_english. Source rank: #50. Votes: 2147. Organization: moonshot. License: Modified MIT.

87.3% percentile inside its fair comparison set

1,449Raw benchmark valueCI 1,437 - 1,462

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 #31 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,431
Percentile: 90.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: instruction_following. Source rank: #39. Votes: 2232. Organization: moonshot. License: Modified MIT.

90.8% percentile inside its fair comparison set

1,431Raw benchmark valueCI 1,419 - 1,443

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 #39 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,438
Percentile: 87.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: longer_query. Source rank: #47. Votes: 2211. Organization: moonshot. License: Modified MIT.

87.5% percentile inside its fair comparison set

1,438Raw benchmark valueCI 1,426 - 1,450

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 #58 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,426
Percentile: 82.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: multi_turn. Source rank: #72. Votes: 1467. Organization: moonshot. License: Modified MIT.

82.4% percentile inside its fair comparison set

1,426Raw benchmark valueCI 1,411 - 1,441

Coding7 benchmarks62.3%

Code Arena

AR · Coding · Human

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

Rank #29 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,408
Percentile: 61.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: overall. Source rank: #37. Votes: 3610. Organization: moonshot. License: Modified MIT.

61.6% percentile inside its fair comparison set

1,408Raw benchmark valueCI 1,397 - 1,418

WebDev Arena

AR · Coding · Human

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

Rank #29 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,408
Percentile: 61.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: webdev. Source rank: #37. Votes: 3610. Organization: moonshot. License: Modified MIT.

61.6% percentile inside its fair comparison set

1,408Raw benchmark valueCI 1,397 - 1,418

Code Arena · Webdev Html

AR · Coding · Human

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

Rank #31 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,413
Percentile: 58.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: webdev-html. Source rank: #39. Votes: 590. Organization: moonshot. License: Modified MIT.

58.9% percentile inside its fair comparison set

1,413Raw benchmark valueCI 1,389 - 1,438

Code Arena · Webdev React

AR · Coding · Human

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

Rank #30 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,396
Percentile: 50.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: webdev-react. Source rank: #38. Votes: 3020. Organization: moonshot. License: Modified MIT.

50.8% percentile inside its fair comparison set

1,396Raw benchmark valueCI 1,384 - 1,407

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 #29 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,505
Percentile: 91.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: coding. Source rank: #38. Votes: 1800. Organization: moonshot. License: Modified MIT.

91.3% percentile inside its fair comparison set

1,505Raw benchmark valueCI 1,491 - 1,519

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 #19 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,484
Percentile: 94.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: coding. Source rank: #24. Votes: 1800. Organization: moonshot. License: Modified MIT.

94.4% percentile inside its fair comparison set

1,484Raw benchmark valueCI 1,470 - 1,498

Code Arena · Image To Webdev

AR · Coding · Human

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

Rank #15 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,415
Percentile: 17.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: image_to_webdev. Source rank: #19. Votes: 1093. Organization: moonshot. License: Modified MIT.

17.6% percentile inside its fair comparison set

1,415Raw benchmark valueCI 1,395 - 1,435

Reasoning / math / science2 benchmarks88.2%

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 #40 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,442
Percentile: 87.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: math. Source rank: #51. Votes: 513. Organization: moonshot. License: Modified MIT.

87.6% percentile inside its fair comparison set

1,442Raw benchmark valueCI 1,417 - 1,467

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 #36 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,441
Percentile: 88.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: math. Source rank: #44. Votes: 513. Organization: moonshot. License: Modified MIT.

88.9% percentile inside its fair comparison set

1,441Raw benchmark valueCI 1,417 - 1,466

Professional reasoning18 benchmarks81.4%

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #54 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,455
Percentile: 80.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: expert. Source rank: #70. Votes: 562. Organization: moonshot. License: Modified MIT.

80.7% percentile inside its fair comparison set

1,455Raw benchmark valueCI 1,431 - 1,479

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 #60 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,425
Percentile: 81.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: industry_business_and_management_and_financial_operations. Source rank: #76. Votes: 1482. Organization: moonshot. License: Modified MIT.

81.4% percentile inside its fair comparison set

1,425Raw benchmark valueCI 1,410 - 1,441

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 #57 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,401
Percentile: 82.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: industry_entertainment_and_sports_and_media. Source rank: #70. Votes: 1430. Organization: moonshot. License: Modified MIT.

82.7% percentile inside its fair comparison set

1,401Raw benchmark valueCI 1,386 - 1,416

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #52 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,446
Percentile: 82.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: industry_legal_and_government. Source rank: #68. Votes: 514. Organization: moonshot. License: Modified MIT.

82.9% percentile inside its fair comparison set

1,446Raw benchmark valueCI 1,421 - 1,471

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 #52 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,453
Percentile: 84.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: industry_life_and_physical_and_social_science. Source rank: #65. Votes: 1198. Organization: moonshot. License: Modified MIT.

84.2% percentile inside its fair comparison set

1,453Raw benchmark valueCI 1,436 - 1,470

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #48 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,443
Percentile: 84.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: industry_mathematical. Source rank: #60. Votes: 333. Organization: moonshot. License: Modified MIT.

84.7% percentile inside its fair comparison set

1,443Raw benchmark valueCI 1,412 - 1,475

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #80 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,435
Percentile: 73.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: industry_medicine_and_healthcare. Source rank: #98. Votes: 540. Organization: moonshot. License: Modified MIT.

73.2% percentile inside its fair comparison set

1,435Raw benchmark valueCI 1,410 - 1,460

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 #33 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,490
Percentile: 90.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: industry_software_and_it_services. Source rank: #42. Votes: 2852. Organization: moonshot. License: Modified MIT.

90.2% percentile inside its fair comparison set

1,490Raw benchmark valueCI 1,479 - 1,501

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 #63 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,405
Percentile: 80.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: industry_writing_and_literature_and_language. Source rank: #80. Votes: 1846. Organization: moonshot. License: Modified MIT.

80.9% percentile inside its fair comparison set

1,405Raw benchmark valueCI 1,391 - 1,418

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #50 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,441
Percentile: 82.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: expert. Source rank: #59. Votes: 562. Organization: moonshot. License: Modified MIT.

82.2% percentile inside its fair comparison set

1,441Raw benchmark valueCI 1,417 - 1,465

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 #75 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,405
Percentile: 76.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: industry_business_and_management_and_financial_operations. Source rank: #90. Votes: 1482. Organization: moonshot. License: Modified MIT.

76.7% percentile inside its fair comparison set

1,405Raw benchmark valueCI 1,390 - 1,420

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 #64 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,391
Percentile: 80.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: industry_entertainment_and_sports_and_media. Source rank: #77. Votes: 1430. Organization: moonshot. License: Modified MIT.

80.5% percentile inside its fair comparison set

1,391Raw benchmark valueCI 1,376 - 1,406

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 #58 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,431
Percentile: 80.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: industry_legal_and_government. Source rank: #71. Votes: 514. Organization: moonshot. License: Modified MIT.

80.9% percentile inside its fair comparison set

1,431Raw benchmark valueCI 1,406 - 1,456

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 #73 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,430
Percentile: 77.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: industry_life_and_physical_and_social_science. Source rank: #87. Votes: 1198. Organization: moonshot. License: Modified MIT.

77.7% percentile inside its fair comparison set

1,430Raw benchmark valueCI 1,414 - 1,447

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #45 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,441
Percentile: 85.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: industry_mathematical. Source rank: #54. Votes: 333. Organization: moonshot. License: Modified MIT.

85.7% percentile inside its fair comparison set

1,441Raw benchmark valueCI 1,409 - 1,472

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 #94 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,408
Percentile: 68.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: industry_medicine_and_healthcare. Source rank: #113. Votes: 540. Organization: moonshot. License: Modified MIT.

68.5% percentile inside its fair comparison set

1,408Raw benchmark valueCI 1,383 - 1,433

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 #25 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,471
Percentile: 92.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: industry_software_and_it_services. Source rank: #31. Votes: 2852. Organization: moonshot. License: Modified MIT.

92.6% percentile inside its fair comparison set

1,471Raw benchmark valueCI 1,460 - 1,481

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 #65 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,397
Percentile: 80.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: industry_writing_and_literature_and_language. Source rank: #78. Votes: 1846. Organization: moonshot. License: Modified MIT.

80.2% percentile inside its fair comparison set

1,397Raw benchmark valueCI 1,384 - 1,411

Vision understanding12 benchmarks63.8%

Vision Arena

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #28 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,238
Percentile: 75.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: overall. Source rank: #36. Votes: 3892. Organization: moonshot. License: Modified MIT.

75.2% percentile inside its fair comparison set

1,238Raw benchmark valueCI 1,227 - 1,249

Vision Arena · Creative Writing Vision

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #27 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,236
Percentile: 52.7%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: creative_writing_vision. Source rank: #34. Votes: 247. Organization: moonshot. License: Modified MIT.

52.7% percentile inside its fair comparison set

1,236Raw benchmark valueCI 1,200 - 1,272

Vision Arena · Diagram

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #33 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,250
Percentile: 54.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: diagram. Source rank: #43. Votes: 911. Organization: moonshot. License: Modified MIT.

54.3% percentile inside its fair comparison set

1,250Raw benchmark valueCI 1,231 - 1,270

Vision Arena · English

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #29 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,238
Percentile: 74.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: english. Source rank: #37. Votes: 1578. Organization: moonshot. License: Modified MIT.

74.3% percentile inside its fair comparison set

1,238Raw benchmark valueCI 1,222 - 1,254

Vision Arena · Homework

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #34 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,249
Percentile: 51.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: homework. Source rank: #45. Votes: 562. Organization: moonshot. License: Modified MIT.

51.5% percentile inside its fair comparison set

1,249Raw benchmark valueCI 1,226 - 1,273

Vision Arena · Ocr

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #30 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,246
Percentile: 58.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: ocr. Source rank: #39. Votes: 2593. Organization: moonshot. License: Modified MIT.

58.6% percentile inside its fair comparison set

1,246Raw benchmark valueCI 1,234 - 1,258

Vision Arena · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #24 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,255
Percentile: 78.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: overall. Source rank: #31. Votes: 3892. Organization: moonshot. License: Modified MIT.

78.9% percentile inside its fair comparison set

1,255Raw benchmark valueCI 1,244 - 1,266

Vision Arena · Creative Writing Vision · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #24 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,249
Percentile: 58.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: creative_writing_vision. Source rank: #31. Votes: 247. Organization: moonshot. License: Modified MIT.

58.2% percentile inside its fair comparison set

1,249Raw benchmark valueCI 1,213 - 1,285

Vision Arena · Diagram · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #29 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,258
Percentile: 60%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: diagram. Source rank: #37. Votes: 911. Organization: moonshot. License: Modified MIT.

60% percentile inside its fair comparison set

1,258Raw benchmark valueCI 1,239 - 1,278

Vision Arena · English · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #24 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,259
Percentile: 78.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: english. Source rank: #29. Votes: 1578. Organization: moonshot. License: Modified MIT.

78.9% percentile inside its fair comparison set

1,259Raw benchmark valueCI 1,243 - 1,274

Vision Arena · Homework · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #31 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,262
Percentile: 55.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: homework. Source rank: #39. Votes: 562. Organization: moonshot. License: Modified MIT.

55.9% percentile inside its fair comparison set

1,262Raw benchmark valueCI 1,239 - 1,286

Vision Arena · Ocr · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #24 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,261
Percentile: 67.1%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: ocr. Source rank: #30. Votes: 2593. Organization: moonshot. License: Modified MIT.

67.1% percentile inside its fair comparison set

1,261Raw benchmark valueCI 1,248 - 1,273

Multilingual14 benchmarks78.2%

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #56 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,473
Percentile: 81.4%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: chinese. Source rank: #68. Votes: 238. Organization: moonshot. License: Modified MIT.

81.4% percentile inside its fair comparison set

1,473Raw benchmark valueCI 1,435 - 1,512

Text Arena · French

AR · Multilingual · Human

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

Rank #91 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,418
Percentile: 58.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: french. Source rank: #111. Votes: 152. Organization: moonshot. License: Modified MIT.

58.3% percentile inside its fair comparison set

1,418Raw benchmark valueCI 1,370 - 1,466

Text Arena · German

AR · Multilingual · Human

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

Rank #40 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,438
Percentile: 83.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: german. Source rank: #54. Votes: 135. Organization: moonshot. License: Modified MIT.

83.5% percentile inside its fair comparison set

1,438Raw benchmark valueCI 1,390 - 1,485

Text Arena · Korean

AR · Multilingual · Human

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

Rank #47 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,387
Percentile: 77.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: korean. Source rank: #60. Votes: 130. Organization: moonshot. License: Modified MIT.

77.9% percentile inside its fair comparison set

1,387Raw benchmark valueCI 1,339 - 1,436

Text Arena · Russian

AR · Multilingual · Human

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

Rank #58 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,425
Percentile: 80.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: russian. Source rank: #76. Votes: 860. Organization: moonshot. License: Modified MIT.

80.3% percentile inside its fair comparison set

1,425Raw benchmark valueCI 1,406 - 1,444

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #42 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,439
Percentile: 80.8%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: spanish. Source rank: #52. Votes: 257. Organization: moonshot. License: Modified MIT.

80.8% percentile inside its fair comparison set

1,439Raw benchmark valueCI 1,403 - 1,476

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #59 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,462
Percentile: 80.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: chinese. Source rank: #71. Votes: 238. Organization: moonshot. License: Modified MIT.

80.3% percentile inside its fair comparison set

1,462Raw benchmark valueCI 1,424 - 1,499

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #91 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,404
Percentile: 58.3%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: french. Source rank: #109. Votes: 152. Organization: moonshot. License: Modified MIT.

58.3% percentile inside its fair comparison set

1,404Raw benchmark valueCI 1,356 - 1,451

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #59 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,414
Percentile: 75.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: german. Source rank: #74. Votes: 135. Organization: moonshot. License: Modified MIT.

75.5% percentile inside its fair comparison set

1,414Raw benchmark valueCI 1,367 - 1,461

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #49 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,382
Percentile: 76.9%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: korean. Source rank: #59. Votes: 130. Organization: moonshot. License: Modified MIT.

76.9% percentile inside its fair comparison set

1,382Raw benchmark valueCI 1,334 - 1,431

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #69 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,404
Percentile: 76.5%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: russian. Source rank: #86. Votes: 860. Organization: moonshot. License: Modified MIT.

76.5% percentile inside its fair comparison set

1,404Raw benchmark valueCI 1,385 - 1,423

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #36 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,443
Percentile: 83.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: spanish. Source rank: #43. Votes: 257. Organization: moonshot. License: Modified MIT.

83.6% percentile inside its fair comparison set

1,443Raw benchmark valueCI 1,406 - 1,480

Vision Arena · Chinese

AR · Multilingual · Human

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

Rank #7 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,324
Percentile: 92.2%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: chinese. Source rank: #9. Votes: 170. Organization: moonshot. License: Modified MIT.

92.2% percentile inside its fair comparison set

1,324Raw benchmark valueCI 1,280 - 1,368

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #9 · Source label: kimi-k2.5-instant

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,343
Percentile: 89.6%
Last updated: recent
Eligibility: benchmark_derived_model

Parsed from Arena leaderboard dataset row `kimi-k2.5-instant`. Category: chinese. Source rank: #13. Votes: 170. Organization: moonshot. License: Modified MIT.

89.6% percentile inside its fair comparison set

1,343Raw benchmark valueCI 1,300 - 1,387

Source links and registry checks

official

Arena

Jun 20, 2026

kimi-k2.5-instant

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks

Loading model evidence.

kimi-k2.5-instant

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks