Model profile · Unknown

minimax-m2.1-preview

Unknown weightsmid · registry tag 2026 benchmark-derived

Thin verified coverage

Reads as thin verified coverage across the resolved source data.

Visible coverage: 2.1%
Verified coverage: 2.1%
Spread: n/a
Last verified: Jun 20, 2026

textcode2 aliases31 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 benchmarks69.7%

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 #115 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,384
Percentile: 64.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: overall. Source rank: #140. Votes: 17128. Organization: minimax. License: MIT.

64.9% percentile inside its fair comparison set

1,384Raw benchmark valueCI 1,379 - 1,390

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 #115 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,346
Percentile: 64.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: creative_writing. Source rank: #140. Votes: 2716. Organization: minimax. License: MIT.

64.7% percentile inside its fair comparison set

1,346Raw benchmark valueCI 1,334 - 1,357

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 #113 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,402
Percentile: 65.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: english. Source rank: #136. Votes: 7641. Organization: minimax. License: MIT.

65.5% percentile inside its fair comparison set

1,402Raw benchmark valueCI 1,395 - 1,409

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 #118 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,357
Percentile: 64%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: exclude_ties. Source rank: #143. Votes: 12077. Organization: minimax. License: MIT.

64% percentile inside its fair comparison set

1,357Raw benchmark valueCI 1,350 - 1,365

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 #111 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,408
Percentile: 66.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: hard_prompts. Source rank: #135. Votes: 9069. Organization: minimax. License: MIT.

66.2% percentile inside its fair comparison set

1,408Raw benchmark valueCI 1,401 - 1,414

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 #103 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,425
Percentile: 68.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: hard_prompts_english. Source rank: #123. Votes: 4200. Organization: minimax. License: MIT.

68.5% percentile inside its fair comparison set

1,425Raw benchmark valueCI 1,416 - 1,434

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 #100 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,386
Percentile: 69.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: instruction_following. Source rank: #123. Votes: 4473. Organization: minimax. License: MIT.

69.5% percentile inside its fair comparison set

1,386Raw benchmark valueCI 1,377 - 1,395

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 #92 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,410
Percentile: 70.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: longer_query. Source rank: #116. Votes: 4256. Organization: minimax. License: MIT.

70.1% percentile inside its fair comparison set

1,410Raw benchmark valueCI 1,401 - 1,419

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 #109 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,391
Percentile: 66.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: multi_turn. Source rank: #132. Votes: 2872. Organization: minimax. License: MIT.

66.6% percentile inside its fair comparison set

1,391Raw benchmark valueCI 1,380 - 1,402

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 #102 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,391
Percentile: 68.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: overall. Source rank: #123. Votes: 17128. Organization: minimax. License: MIT.

68.9% percentile inside its fair comparison set

1,391Raw benchmark valueCI 1,386 - 1,396

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 #92 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,362
Percentile: 71.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: creative_writing. Source rank: #113. Votes: 2716. Organization: minimax. License: MIT.

71.8% percentile inside its fair comparison set

1,362Raw benchmark valueCI 1,351 - 1,374

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 #99 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,406
Percentile: 69.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: english. Source rank: #120. Votes: 7641. Organization: minimax. License: MIT.

69.8% percentile inside its fair comparison set

1,406Raw benchmark valueCI 1,399 - 1,413

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 #102 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,367
Percentile: 68.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: exclude_ties. Source rank: #123. Votes: 12077. Organization: minimax. License: MIT.

68.9% percentile inside its fair comparison set

1,367Raw benchmark valueCI 1,359 - 1,374

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 #89 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,410
Percentile: 72.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: hard_prompts. Source rank: #106. Votes: 9069. Organization: minimax. License: MIT.

72.9% percentile inside its fair comparison set

1,410Raw benchmark valueCI 1,404 - 1,417

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 #80 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,423
Percentile: 75.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: hard_prompts_english. Source rank: #96. Votes: 4200. Organization: minimax. License: MIT.

75.6% percentile inside its fair comparison set

1,423Raw benchmark valueCI 1,414 - 1,432

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 #75 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,398
Percentile: 77.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: instruction_following. Source rank: #91. Votes: 4473. Organization: minimax. License: MIT.

77.2% percentile inside its fair comparison set

1,398Raw benchmark valueCI 1,390 - 1,407

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 #64 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,418
Percentile: 79.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: longer_query. Source rank: #77. Votes: 4256. Organization: minimax. License: MIT.

79.3% percentile inside its fair comparison set

1,418Raw benchmark valueCI 1,409 - 1,427

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 #95 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,394
Percentile: 70.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: multi_turn. Source rank: #116. Votes: 2872. Organization: minimax. License: MIT.

70.9% percentile inside its fair comparison set

1,394Raw benchmark valueCI 1,383 - 1,405

Coding6 benchmarks56.6%

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 #37 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,392
Percentile: 50.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: overall. Source rank: #44. Votes: 9273. Organization: minimax. License: MIT.

50.7% percentile inside its fair comparison set

1,392Raw benchmark valueCI 1,384 - 1,400

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 #37 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,392
Percentile: 50.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: webdev. Source rank: #44. Votes: 9273. Organization: minimax. License: MIT.

50.7% percentile inside its fair comparison set

1,392Raw benchmark valueCI 1,384 - 1,400

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 #33 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,404
Percentile: 56.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: webdev-html. Source rank: #41. Votes: 6772. Organization: minimax. License: MIT.

56.2% percentile inside its fair comparison set

1,404Raw benchmark valueCI 1,393 - 1,415

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 #36 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,373
Percentile: 40.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: webdev-react. Source rank: #46. Votes: 2492. Organization: minimax. License: MIT.

40.7% percentile inside its fair comparison set

1,373Raw benchmark valueCI 1,360 - 1,386

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 #103 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,439
Percentile: 68.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: coding. Source rank: #124. Votes: 3427. Organization: minimax. License: MIT.

68.1% percentile inside its fair comparison set

1,439Raw benchmark valueCI 1,429 - 1,449

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 #86 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,423
Percentile: 73.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: coding. Source rank: #103. Votes: 3427. Organization: minimax. License: MIT.

73.4% percentile inside its fair comparison set

1,423Raw benchmark valueCI 1,413 - 1,433

Reasoning / math / science2 benchmarks66.2%

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 #109 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,392
Percentile: 65.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: math. Source rank: #132. Votes: 1010. Organization: minimax. License: MIT.

65.6% percentile inside its fair comparison set

1,392Raw benchmark valueCI 1,374 - 1,411

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 #105 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,395
Percentile: 66.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: math. Source rank: #125. Votes: 1010. Organization: minimax. License: MIT.

66.9% percentile inside its fair comparison set

1,395Raw benchmark valueCI 1,376 - 1,413

Professional reasoning18 benchmarks69%

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #81 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,432
Percentile: 70.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: expert. Source rank: #100. Votes: 1055. Organization: minimax. License: MIT.

70.9% percentile inside its fair comparison set

1,432Raw benchmark valueCI 1,414 - 1,450

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 #113 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,381
Percentile: 64.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: industry_business_and_management_and_financial_operations. Source rank: #137. Votes: 3149. Organization: minimax. License: MIT.

64.8% percentile inside its fair comparison set

1,381Raw benchmark valueCI 1,370 - 1,392

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 #110 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,350
Percentile: 66.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: industry_entertainment_and_sports_and_media. Source rank: #134. Votes: 3203. Organization: minimax. License: MIT.

66.3% percentile inside its fair comparison set

1,350Raw benchmark valueCI 1,340 - 1,361

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #108 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,399
Percentile: 64.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: industry_legal_and_government. Source rank: #131. Votes: 1183. Organization: minimax. License: MIT.

64.1% percentile inside its fair comparison set

1,399Raw benchmark valueCI 1,381 - 1,416

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 #111 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,406
Percentile: 65.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: industry_life_and_physical_and_social_science. Source rank: #134. Votes: 2656. Organization: minimax. License: MIT.

65.9% percentile inside its fair comparison set

1,406Raw benchmark valueCI 1,394 - 1,418

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #80 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,420
Percentile: 74.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: industry_mathematical. Source rank: #97. Votes: 652. Organization: minimax. License: MIT.

74.4% percentile inside its fair comparison set

1,420Raw benchmark valueCI 1,398 - 1,441

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #137 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,376
Percentile: 53.9%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: industry_medicine_and_healthcare. Source rank: #164. Votes: 1130. Organization: minimax. License: MIT.

53.9% percentile inside its fair comparison set

1,376Raw benchmark valueCI 1,358 - 1,395

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 #111 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,423
Percentile: 66.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: industry_software_and_it_services. Source rank: #134. Votes: 5788. Organization: minimax. License: MIT.

66.2% percentile inside its fair comparison set

1,423Raw benchmark valueCI 1,415 - 1,431

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 #113 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,365
Percentile: 65.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: industry_writing_and_literature_and_language. Source rank: #138. Votes: 3922. Organization: minimax. License: MIT.

65.4% percentile inside its fair comparison set

1,365Raw benchmark valueCI 1,355 - 1,374

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #49 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,441
Percentile: 82.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: expert. Source rank: #58. Votes: 1055. Organization: minimax. License: MIT.

82.5% percentile inside its fair comparison set

1,441Raw benchmark valueCI 1,423 - 1,459

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 #96 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,391
Percentile: 70.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: industry_business_and_management_and_financial_operations. Source rank: #114. Votes: 3149. Organization: minimax. License: MIT.

70.1% percentile inside its fair comparison set

1,391Raw benchmark valueCI 1,380 - 1,401

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 #91 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,362
Percentile: 72.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: industry_entertainment_and_sports_and_media. Source rank: #111. Votes: 3203. Organization: minimax. License: MIT.

72.1% percentile inside its fair comparison set

1,362Raw benchmark valueCI 1,351 - 1,372

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 #86 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,411
Percentile: 71.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: industry_legal_and_government. Source rank: #104. Votes: 1183. Organization: minimax. License: MIT.

71.5% percentile inside its fair comparison set

1,411Raw benchmark valueCI 1,395 - 1,428

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 #94 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,416
Percentile: 71.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: industry_life_and_physical_and_social_science. Source rank: #111. Votes: 2656. Organization: minimax. License: MIT.

71.2% percentile inside its fair comparison set

1,416Raw benchmark valueCI 1,405 - 1,427

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #75 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,419
Percentile: 76%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: industry_mathematical. Source rank: #90. Votes: 652. Organization: minimax. License: MIT.

76% percentile inside its fair comparison set

1,419Raw benchmark valueCI 1,398 - 1,441

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 #108 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,389
Percentile: 63.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: industry_medicine_and_healthcare. Source rank: #130. Votes: 1130. Organization: minimax. License: MIT.

63.7% percentile inside its fair comparison set

1,389Raw benchmark valueCI 1,371 - 1,407

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 #95 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,415
Percentile: 71.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: industry_software_and_it_services. Source rank: #113. Votes: 5788. Organization: minimax. License: MIT.

71.1% percentile inside its fair comparison set

1,415Raw benchmark valueCI 1,407 - 1,423

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 #93 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,372
Percentile: 71.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: industry_writing_and_literature_and_language. Source rank: #115. Votes: 3922. Organization: minimax. License: MIT.

71.6% percentile inside its fair comparison set

1,372Raw benchmark valueCI 1,363 - 1,382

Multilingual14 benchmarks56.6%

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #104 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,415
Percentile: 65.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: chinese. Source rank: #127. Votes: 820. Organization: minimax. License: MIT.

65.1% percentile inside its fair comparison set

1,415Raw benchmark valueCI 1,394 - 1,436

Text Arena · French

AR · Multilingual · Human

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

Rank #101 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,406
Percentile: 53.7%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: french. Source rank: #121. Votes: 398. Organization: minimax. License: MIT.

53.7% percentile inside its fair comparison set

1,406Raw benchmark valueCI 1,376 - 1,436

Text Arena · German

AR · Multilingual · Human

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

Rank #95 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,380
Percentile: 60.3%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: german. Source rank: #115. Votes: 268. Organization: minimax. License: MIT.

60.3% percentile inside its fair comparison set

1,380Raw benchmark valueCI 1,343 - 1,417

Text Arena · Japanese

AR · Multilingual · Human

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

Rank #113 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,281
Percentile: 44.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: japanese. Source rank: #141. Votes: 146. Organization: minimax. License: MIT.

44.8% percentile inside its fair comparison set

1,281Raw benchmark valueCI 1,228 - 1,334

Text Arena · Korean

AR · Multilingual · Human

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

Rank #129 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,277
Percentile: 38.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: korean. Source rank: #158. Votes: 268. Organization: minimax. License: MIT.

38.5% percentile inside its fair comparison set

1,277Raw benchmark valueCI 1,238 - 1,316

Text Arena · Russian

AR · Multilingual · Human

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

Rank #102 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,384
Percentile: 65.1%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: russian. Source rank: #125. Votes: 1913. Organization: minimax. License: MIT.

65.1% percentile inside its fair comparison set

1,384Raw benchmark valueCI 1,371 - 1,397

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #105 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,377
Percentile: 51.4%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: spanish. Source rank: #128. Votes: 407. Organization: minimax. License: MIT.

51.4% percentile inside its fair comparison set

1,377Raw benchmark valueCI 1,347 - 1,408

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #91 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,429
Percentile: 69.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: chinese. Source rank: #109. Votes: 820. Organization: minimax. License: MIT.

69.5% percentile inside its fair comparison set

1,429Raw benchmark valueCI 1,409 - 1,450

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #90 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,404
Percentile: 58.8%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: french. Source rank: #108. Votes: 398. Organization: minimax. License: MIT.

58.8% percentile inside its fair comparison set

1,404Raw benchmark valueCI 1,374 - 1,434

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #92 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,379
Percentile: 61.6%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: german. Source rank: #110. Votes: 268. Organization: minimax. License: MIT.

61.6% percentile inside its fair comparison set

1,379Raw benchmark valueCI 1,342 - 1,415

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #102 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,288
Percentile: 50.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: japanese. Source rank: #124. Votes: 146. Organization: minimax. License: MIT.

50.2% percentile inside its fair comparison set

1,288Raw benchmark valueCI 1,237 - 1,340

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #117 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,288
Percentile: 44.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: korean. Source rank: #140. Votes: 268. Organization: minimax. License: MIT.

44.2% percentile inside its fair comparison set

1,288Raw benchmark valueCI 1,251 - 1,325

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #92 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,386
Percentile: 68.5%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: russian. Source rank: #112. Votes: 1913. Organization: minimax. License: MIT.

68.5% percentile inside its fair comparison set

1,386Raw benchmark valueCI 1,373 - 1,399

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #84 · Source label: minimax-m2.1-preview

verified runtimeexact aliasBackground only

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,401
Percentile: 61.2%
Last updated: recent
Eligibility: preview_model

Parsed from Arena leaderboard dataset row `minimax-m2.1-preview`. Category: spanish. Source rank: #99. Votes: 407. Organization: minimax. License: MIT.

61.2% percentile inside its fair comparison set

1,401Raw benchmark valueCI 1,371 - 1,431

Source links and registry checks

official

Arena

Jun 20, 2026

minimax-m2.1-preview

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks

Loading model evidence.

minimax-m2.1-preview

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks