Skip to main content
← Benchmark sources

arena.ai · benchmark source

Arena

Live human-preference and agent boards from Arena (LMArena). Scores are board-specific — Text Arena Score, WebDev Arena Score, and Agent net improvement are not interchangeable.

Open arena.ai3 boards on this publisher

General chat

Text Arena · Overall

Arena's overall text-to-text preference leaderboard across math, coding, creative writing, and other open-ended tasks, scored with Arena Score (Bradley-Terry / Elo-style).

Why it matters

It is the broadest live preference signal for general chat quality when you need an orienting shortlist before task-specific benchmarks.

Use it when

You are shortlisting models for general assistant or chat work and want a live preference signal with honest coverage limits.

The limitation

Votes reflect crowd taste on open-ended prompts, not factual accuracy, agent tool use, or enterprise safety. Arena Score is board-specific and not comparable to WebDev or Agent net improvement.

Leaderboard snapshot

Text Arena · Overall results in a readable view

Use the tabs for the primary score and other published fields from this board. The source link remains authoritative for the live table.

Full Arena Text board mirrored — hundreds of models, not a catalog shortlist.

Local leader

claude-fable-5

1,507

Rows shown

390

Arena Score

Snapshot date

2026-08-12

3 days old · not a live API feed

Score profile

Arena Score by published row

Higher is better in this view

claude-fable-5
1,507
claude-opus-4-6-thinking
1,505
claude-opus-4-7-thinking
1,502
muse-spark-1.2 (xHigh)
1,498
claude-opus-4-6
1,497
claude-opus-4-7
1,494
claude-opus-5-high
1,494
claude-opus-5-max
1,491
gemini-3.7-flash-high
1,490
qwen3.8-max
1,490
muse-spark-1.1
1,489
muse-spark
1,488
kimi-k3-max
1,487
gemini-3.1-pro-preview
1,486
gemini-3-pro
1,485
gemini-3.6-flash
1,484
claude-opus-4-8-thinking
1,482
gpt-5.5-high
1,481
gpt-5.6-sol-xhigh
1,481
gemini-3.5-flash-high
1,477
gpt-5.4-high
1,477
gpt-5.5
1,477
gpt-5.2-chat-latest-20260210
1,476
gemini-3.5-flash-medium
1,475
grok-4.20-beta1
1,475
qwen3.7-max-preview
1,474
claude-opus-4-5-20251101-thinking-32k
1,473
claude-opus-4-8
1,473
gemini-3-flash
1,473
gpt-5.5-instant
1,473
claude-sonnet-4-6
1,472
grok-4.20-beta-0309-reasoning
1,472
glm-5.2-max
1,470
grok-4.20-multi-agent-beta-0309
1,470
claude-opus-4-5-20251101
1,469
grok-4.5
1,469
ernie-5.1
1,468
mimo-v2.5-pro
1,468
glm-5.1
1,467
gpt-5.4
1,466
grok-4.1-thinking
1,465
qwen3.5-max-preview
1,465
gpt-5.6-terra-xhigh
1,464
grok-4.6-high
1,464
claude-sonnet-5-high
1,463
kimi-k2.6
1,460
qwen3.6-max-preview
1,460
gemini-3.5-flash-lite
1,459
grok-4.1
1,459
deepseek-v4-pro
1,458
gemini-3-flash (thinking-minimal)
1,458
qwen3.7-plus
1,458
glm-5
1,457
hy3
1,457
claude-sonnet-4-5-20250929-thinking-32k
1,456
deepseek-v4-pro-high-preview
1,456
dola-seed-2.0-pro
1,456
claude-sonnet-4-5-20250929
1,455
gpt-5.1-high
1,455
gemma-4-31b
1,451
gpt-5.6-luna-xhigh
1,451
kimi-k2.5-thinking
1,450
claude-opus-4-1-20250805-thinking-16k
1,449
ernie-5.0-preview-1203
1,449
gpt-5.3-chat-latest
1,449
gpt-5.4-mini-high
1,448
mimo-v2-pro
1,448
claude-opus-4-1-20250805
1,447
ernie-5.0-0110
1,446
gemini-2.5-pro
1,445
gpt-4.5-preview-2025-02-27
1,445
qwen3.6-plus
1,444
chatgpt-4o-latest-20250326
1,443
minimax-m3
1,443
glm-4.7
1,442
grok-4.3
1,442
inkling
1,442
qwen3.5-397b-a17b
1,442
gpt-5.1
1,439
deepseek-v4-flash-high-preview
1,438
gemma-4-26b-a4b
1,438
gpt-5.2-high
1,437
longcat-flash-chat-2602-exp
1,436
deepseek-v4-flash
1,435
gpt-5.2
1,435
gpt-5-high
1,434
mimo-v2.5
1,434
qwen3-max-preview
1,434
glm-5v-turbo
1,433
gemini-3.1-flash-lite-preview
1,432
grok-4-1-fast-reasoning
1,431
kimi-k2.5-instant
1,431
o3-2025-04-16
1,431
kimi-k2-thinking-turbo
1,430
mimo-v2-omni
1,430
gpt-5-chat
1,427
mistral-medium-3.5
1,427
amazon-nova-experimental-chat-26-02-10
1,426
muse-glimmer
1,426
nvidia-nemotron-3-ultra-550b-a55b-nvfp4
1,426
claude-opus-4-20250514-thinking-16k
1,425
deepseek-v3.2
1,425
deepseek-v3.2-exp-thinking
1,425
glm-4.6
1,424
qwen3-max-2025-09-23
1,424
deepseek-v3.2-thinking
1,423
qwen3-235b-a22b-instruct-2507
1,423
deepseek-r1-0528
1,422
deepseek-v3.2-exp
1,422
grok-4-fast-chat
1,420
ernie-5.0-preview-1022
1,418
kimi-k2-0711-preview
1,418
kimi-k2-0905-preview
1,418
deepseek-v3.1
1,417
deepseek-v3.1-terminus-thinking
1,417
qwen3.5-122b-a10b
1,417
deepseek-v3.1-thinking
1,416
minimax-m2.7
1,416
amazon-nova-experimental-chat-26-01-10
1,415
deepseek-v3.1-terminus
1,415
mistral-large-3
1,415
gpt-4.1-2025-04-14
1,414
qwen3-vl-235b-a22b-instruct
1,414
hunyuan-hy3-preview
1,413
claude-haiku-4-5-20251001
1,412
claude-opus-4-20250514
1,412
glm-4.5
1,411
grok-3-preview-02-24
1,411
gemini-2.5-flash
1,410
grok-4-0709
1,409
mistral-medium-2508
1,409
qwen3.5-27b
1,408
gemini-2.5-flash-preview-09-2025
1,404
grok-4-fast-reasoning
1,404
qwen3-235b-a22b-no-thinking
1,403
gpt-5.4-nano-high
1,402
o1-2024-12-17
1,402
longcat-flash-chat
1,401
qwen3-next-80b-a3b-instruct
1,401
claude-sonnet-4-20250514-thinking-32k
1,400
qwen3-235b-a22b-thinking-2507
1,399
deepseek-r1
1,398
qwen3.5-flash
1,397
deepseek-v3-0324
1,396
hunyuan-vision-1.5-thinking
1,395
qwen3-vl-235b-a22b-thinking
1,395
qwen3.5-35b-a3b
1,395
step-3.5-flash
1,395
amazon-nova-experimental-chat-12-10
1,394
mimo-v2-flash (non-thinking)
1,392
claude-sonnet-4-20250514
1,390
gpt-5-mini-high
1,390
minimax-m2.5
1,390
o4-mini-2025-04-16
1,390
o1-preview
1,389
claude-3-7-sonnet-20250219-thinking-32k
1,388
qwen3-coder-480b-a35b-instruct
1,388
hunyuan-t1-20250711
1,387
mistral-medium-2505
1,387
mimo-v2-flash (thinking)
1,386
minimax-m2.1-preview
1,384
gpt-4.1-mini-2025-04-14
1,383
hunyuan-turbos-20250416
1,383
qwen3-30b-a3b-instruct-2507
1,383
gemini-2.5-flash-lite-preview-09-2025-no-thinking
1,380
trinity-large-preview
1,379
solar-pro4
1,378
glm-4.6v
1,377
gemini-2.5-flash-lite-preview-06-17-thinking
1,375
qwen3-235b-a22b
1,375
qwen2.5-max
1,374
claude-3-5-sonnet-20241022
1,373
glm-4.5-air
1,373
claude-3-7-sonnet-20250219
1,372
qwen3-next-80b-a3b-thinking
1,369
trinity-large-thinking
1,369
glm-4.7-flash
1,367
amazon-nova-experimental-chat-11-10
1,366
gemma-3-27b-it
1,366
o3-mini-high
1,364
minimax-m1
1,363
grok-3-mini-high
1,362
gemini-2.0-flash-001
1,360
nvidia-nemotron-3-super-120b-a12b
1,360
deepseek-v3
1,359
mistral-small-2506
1,357
grok-3-mini-beta
1,356
intellect-3
1,356
command-a-03-2025
1,354
gemini-2.0-flash-lite-preview-02-05
1,354
glm-4.5v
1,353
gpt-oss-120b
1,352
gemini-1.5-pro-002
1,351
amazon-nova-experimental-chat-10-20
1,350
hunyuan-turbos-20250226
1,349
llama-3.1-nemotron-ultra-253b-v1
1,348
o3-mini
1,348
step-3
1,348
amazon-nova-experimental-chat-10-09
1,347
qwen3-32b
1,347
gpt-4o-2024-05-13
1,346
ling-flash-2.0
1,346
mercury-2
1,346
minimax-m2
1,346
qwen-plus-0125
1,346
claude-3-5-sonnet-20240620
1,343
glm-4-plus-0111
1,343
nvidia-llama-3.3-nemotron-super-49b-v1.5
1,343
gemma-3-12b-it
1,342
hunyuan-turbo-0110
1,341
gpt-5-nano-high
1,337
o1-mini
1,337
gemini-advanced-0514
1,336
grok-2-2024-08-13
1,336
nova-2-lite
1,336
qwq-32b
1,336
gpt-4o-2024-08-06
1,335
llama-3.1-405b-instruct-bf16
1,335
nvidia-nemotron-3.5-lightning-30b-a3b-nvfp4
1,335
step-2-16k-exp-202412
1,334
llama-3.1-405b-instruct-fp8
1,333
molmo-2-8b
1,329
olmo-3.1-32b-instruct
1,329
llama-3.3-nemotron-49b-super-v1
1,328
yi-lightning
1,328
llama-4-maverick-17b-128e-instruct
1,327
qwen3-30b-a3b
1,327
hunyuan-large-2025-02-10
1,326
claude-3-5-haiku-20241022
1,324
gemini-1.5-pro-001
1,324
gpt-4-turbo-2024-04-09
1,324
deepseek-v2.5-1210
1,323
claude-3-opus-20240229
1,322
gpt-4.1-nano-2025-04-14
1,322
llama-4-scout-17b-16e-instruct
1,322
ring-flash-2.0
1,320
step-1o-turbo-202506
1,320
glm-4-plus
1,319
gemma-3n-e4b-it
1,318
gpt-4o-mini-2024-07-18
1,318
gpt-oss-20b
1,318
llama-3.3-70b-instruct
1,318
qwen-max-0919
1,318
nvidia-nemotron-3-nano-30b-a3b-bf16
1,315
qwen2.5-plus-1127
1,315
athene-v2-chat
1,314
mistral-large-2407
1,314
gpt-4-0125-preview
1,313
gpt-4-1106-preview
1,312
hunyuan-standard-2025-02-10
1,311
gemini-1.5-flash-002
1,309
grok-2-mini-2024-08-13
1,309
athene-70b-0725
1,307
deepseek-v2.5
1,307
mercury
1,307
granite-4.1-8b
1,306
mistral-large-2411
1,305
olmo-3-32b-think
1,305
magistral-medium-2506
1,304
gemma-3-4b-it
1,303
mistral-small-3.1-24b-instruct-2503
1,303
qwen2.5-72b-instruct
1,303
llama-3.1-nemotron-70b-instruct
1,299
hunyuan-large-vision
1,294
llama-3.1-70b-instruct
1,293
amazon-nova-pro-v1.0
1,290
gemma-2-27b-it
1,289
jamba-1.5-large
1,289
reka-core-20240904
1,288
gpt-4-0314
1,287
ibm-granite-h-small
1,287
gemini-1.5-flash-001
1,286
llama-3.1-nemotron-51b-instruct
1,286
llama-3.1-tulu-3-70b
1,286
olmo-3.1-32b-think
1,285
claude-3-sonnet-20240229
1,281
gemma-2-9b-it-simpo
1,280
nemotron-4-340b-instruct
1,277
command-r-plus-08-2024
1,276
llama-3-70b-instruct
1,276
gpt-4-0613
1,275
mistral-small-24b-instruct-2501
1,274
glm-4-0520
1,273
reka-flash-20240904
1,272
qwen2.5-coder-32b-instruct
1,271
c4ai-aya-expanse-32b
1,267
gemma-2-9b-it
1,267
deepseek-coder-v2
1,265
claude-3-haiku-20240307
1,261
command-r-plus
1,261
qwen2-72b-instruct
1,261
amazon-nova-lite-v1.0
1,260
gemini-1.5-flash-8b-001
1,259
phi-4
1,256
olmo-2-0325-32b-instruct
1,251
command-r-08-2024
1,250
mistral-large-2402
1,242
amazon-nova-micro-v1.0
1,241
jamba-1.5-mini
1,240
ministral-8b-2410
1,237
gemini-pro-dev-api
1,236
qwen1.5-110b-chat
1,234
hunyuan-standard-256k
1,233
qwen1.5-72b-chat
1,233
reka-flash-21b-20240226-online
1,233
mixtral-8x22b-instruct-v0.1
1,229
command-r
1,226
reka-flash-21b-20240226
1,226
gpt-3.5-turbo-0125
1,225
c4ai-aya-expanse-8b
1,223
gemini-pro
1,223
llama-3-8b-instruct
1,223
mistral-medium
1,222
llama-3.1-tulu-3-8b
1,220
yi-1.5-34b-chat
1,213
zephyr-orpo-141b-A35b-v0.1
1,212
llama-3.1-8b-instruct
1,211
granite-3.1-8b-instruct
1,208
gpt-3.5-turbo-1106
1,203
qwen1.5-32b-chat
1,203
gemma-2-2b-it
1,200
mixtral-8x7b-instruct-v0.1
1,197
phi-3-medium-4k-instruct
1,197
dbrx-instruct-preview
1,195
internlm2_5-20b-chat
1,191
qwen1.5-14b-chat
1,191
deepseek-llm-67b-chat
1,184
wizardlm-70b
1,184
yi-34b-chat
1,183
gemma-1.1-7b-it
1,182
granite-3.0-8b-instruct
1,182
openchat-3.5
1,182
openchat-3.5-0106
1,182
granite-3.1-2b-instruct
1,179
snowflake-arctic-instruct
1,179
tulu-2-dpo-70b
1,177
openhermes-2.5-mistral-7b
1,175
vicuna-33b
1,172
phi-3-small-8k-instruct
1,171
starling-lm-7b-beta
1,171
llama-2-70b-chat
1,170
starling-lm-7b-alpha
1,167
llama-3.2-3b-instruct
1,166
nous-hermes-2-mixtral-8x7b-dpo
1,164
granite-3.0-2b-instruct
1,156
llama2-70b-steerlm-chat
1,154
qwq-32b-preview
1,154
dolphin-2.2.1-mistral-7b
1,152
solar-10.7b-instruct-v1.0
1,152
mpt-30b-chat
1,150
mistral-7b-instruct-v0.2
1,149
wizardlm-13b
1,149
falcon-180b-chat
1,147
phi-3-mini-4k-instruct-june-2024
1,143
qwen1.5-7b-chat
1,143
llama-2-13b-chat
1,141
vicuna-13b
1,141
qwen-14b-chat
1,139
palm-2
1,138
gemma-7b-it
1,137
codellama-34b-instruct
1,136
zephyr-7b-beta
1,130
phi-3-mini-128k-instruct
1,129
phi-3-mini-4k-instruct
1,128
guanaco-33b
1,127
zephyr-7b-alpha
1,126
stripedhyena-nous-7b
1,121
codellama-70b-instruct
1,119
gemma-1.1-2b-it
1,116
vicuna-7b
1,115
smollm2-1.7b-instruct
1,114
llama-3.2-1b-instruct
1,111
mistral-7b-instruct
1,110
llama-2-7b-chat
1,108
gemma-2b-it
1,093
qwen1.5-4b-chat
1,090
olmo-7b-instruct
1,073
koala-13b
1,070
alpaca-13b
1,069
gpt4all-13b-snoozy
1,067
mpt-7b-chat
1,063
chatglm3-6b
1,056
RWKV-4-Raven-14B
1,042
chatglm2-6b
1,024
oasst-pythia-12b
1,023
chatglm-6b
995
fastchat-t5-3b
992
dolly-v2-12b
981
llama-13b
974
stablelm-tuned-alpha-7b
953

Full Text Arena overall board mirrored 2026-08-12 from arena.ai/leaderboard/text. Confidence intervals overlap heavily below the top cluster. Arena Score is board-specific and not comparable to WebDev, Agent net improvement, or SWE-bench percentages.

Open Text Arena leaderboard

Evidence in this catalog

Where Text Arena · Overall fits

Closest verified examples we currently carry. A missing score is not a zero.

Model examples

  • Claude Fable 51507 Arena Score

    Text Arena overall board retrieved 2026-08-12.

  • Claude Opus 51494 Arena Score (high)

    Text Arena snapshot retrieved 2026-08-12; multiple effort rows exist on the live board.

  • Gemini 3.6 Flash1484 Arena Score

    Text Arena overall board retrieved 2026-08-12. Gemini 3.6 Flash is marked Preliminary on the live board; this catalogued row is not.

Harness examples

No directly comparable harness score is verified here yet.

Open this board on Text Arena leaderboard