Benchmarks / Arena (formerly LMArena)

Reported by Arena (formerly LMArena)

Arena (formerly LMArena)

Human preference combined with labels of whether each answer's checkable claims were true (factuality weighted 25% by default).

Last updated 2 Oct 2026

Results dated
2 Oct 2026
Results
182 configurations of 163 models
Unit
Arena rating
Licence
Creative Commons Attribution 4.0 International

Overall: Claude Opus 5

Top 16 of 182 results · Arena rating, higher is better · lines show the 95% range · ≈ cannot be told apart from the leader. Choose a model to highlight it.Clear highlight

  1. 1≈ Gemini 4 Argon (high reasoning)Google 1,511
  2. 2≈ Claude Opus 5.5 (high reasoning)Anthropic 1,507
  3. 3≈ Claude Fable 5.1 (max reasoning)Anthropic 1,500
  4. 4 Claude Opus 4.6 (high reasoning)Anthropic 1,494
  5. 5 Claude Opus 5 (max reasoning)Anthropic 1,489
  6. 6 Claude Opus 4.6Anthropic 1,488
  7. 7 GPT-5.5 (high reasoning)OpenAI 1,486
  8. 8 GPT-5.4 (high reasoning)OpenAI 1,485
  9. 9 Claude Fable 5 (high reasoning)Anthropic 1,484
  10. 10 MiMo-V2.6-ProXiaomi 1,483
  11. 10 Muse Spark 1.2 (extra-high reasoning)Meta 1,483
  12. 12 GPT-5.5OpenAI 1,482
  13. 13 Gemini 3 Pro PreviewGoogle 1,481
  14. 13 Qwen3.7-Max-PreviewAlibaba 1,481
  15. 15 Muse Spark 1.3 (max reasoning)Meta 1,480
  16. 16 Claude Opus 5 (high reasoning)Anthropic 1,477

Full results

Arena Text factuality: overall, Arena rating, higher is better
#ModelOverall · 95% range
Arena rating, higher is better		Price
$ per million tokens, in / out
1≈ Gemini 4 Argon (high reasoning)Google
1,511
1,503–1,518
–
2≈ Claude Opus 5.5 (high reasoning)Anthropic
1,507
1,499–1,515
$4 / $20
3≈ Claude Fable 5.1 (max reasoning)Anthropic
1,500
1,494–1,505
$10 / $50
4 Claude Opus 4.6 (high reasoning)Anthropic
1,494
1,491–1,496
$5 / $25
5 Claude Opus 5 (max reasoning)Anthropic
1,489
1,485–1,493
$5 / $25
6 Claude Opus 4.6Anthropic
1,488
1,486–1,491
$5 / $25
7 GPT-5.5 (high reasoning)OpenAI
1,486
1,483–1,489
$5 / $30
8 GPT-5.4 (high reasoning)OpenAI
1,485
1,482–1,488
$2.50 / $15
9 Claude Fable 5 (high reasoning)Anthropic
1,484
1,480–1,487
$10 / $50
10 MiMo-V2.6-ProXiaomi
1,483
1,475–1,491
$0.43 / $0.87
10 Muse Spark 1.2 (extra-high reasoning)Meta
1,483
1,475–1,491
$1.25 / $4.25
12 GPT-5.5OpenAI
1,482
1,479–1,485
$5 / $30
13 Gemini 3 Pro PreviewGoogle
1,481
1,478–1,485
–
13 Qwen3.7-Max-PreviewAlibaba
1,481
1,472–1,489
–
15 Muse Spark 1.3 (max reasoning)Meta
1,480
1,475–1,485
$1.25 / $4.25
16 Claude Opus 5 (high reasoning)Anthropic
1,477
1,474–1,481
$5 / $25
16 Claude Opus 4.7 (high reasoning)Anthropic
1,477
1,474–1,480
$5 / $25
16 Gemini 3.7 Flash (high reasoning)Google
1,477
1,473–1,481
$1.50 / $7.50
16 Gemini 3.8 Flash (high reasoning)Google
1,477
1,472–1,481
$1.50 / $7.50
20 Gemini 3.5 Flash (high reasoning)Google
1,476
1,473–1,480
$1.50 / $9
20 GPT-5.6 Sol (extra-high reasoning)OpenAI
1,476
1,473–1,480
$4 / $20
22 GPT-5.4OpenAI
1,475
1,472–1,478
$2.50 / $15
22 Claude Opus 4.7Anthropic
1,475
1,472–1,478
$5 / $25
22 Qwen3.5-Max-PreviewAlibaba
1,475
1,470–1,479
–
25 Kimi K3 (max reasoning)Moonshot AI
1,472
1,469–1,476
$3 / $15
25 Gemini 3.1 Pro PreviewGoogle
1,472
1,470–1,474
$2 / $12
25 Qwen3.8-Max (0902)Alibaba
1,472
1,467–1,476
$2 / $6
28 Gemini 3.6 Flash (high reasoning)Google
1,471
1,468–1,475
$1.50 / $7.50
29 Claude Sonnet 5.5 (extra-high reasoning)Anthropic
1,470
1,461–1,479
$2 / $10
29 Claude Opus 4.8 (high reasoning)Anthropic
1,470
1,467–1,473
$5 / $25
31 Muse SparkMeta
1,468
1,462–1,473
–
31 Gemini 3 Flash PreviewGoogle
1,468
1,464–1,471
$0.50 / $3
33 DeepSeek-V4.1-Flash (max reasoning)DeepSeek
1,467
1,461–1,473
$0.30 / $1.20
33 GLM-5.3 (max reasoning)Z.ai
1,467
1,462–1,472
$1.40 / $4.40
33 Gemini 3.5 Flash (medium reasoning)Google
1,467
1,463–1,470
$1.50 / $9
36 GPT-5.6 Terra (extra-high reasoning)OpenAI
1,466
1,463–1,470
$2 / $12
36 GPT-6 Astra (max reasoning)OpenAI
1,466
1,460–1,472
$10 / $50
36 GLM-5.3-FlashZ.ai
1,466
1,461–1,470
$0.15 / $0.50
39 Grok 4.5xAI
1,465
1,462–1,469
$2 / $6
39 MiMo-V2.5-ProXiaomi
1,465
1,462–1,468
$0.43 / $0.87
41 Claude Opus 4.8Anthropic
1,464
1,461–1,468
$5 / $25
41 Muse Spark 1.1Meta
1,464
1,460–1,467
$1.25 / $4.25
43 GLM-5.2 (max reasoning)Z.ai
1,463
1,460–1,467
$1.40 / $4.40
43 GPT-6.1 Sol (max reasoning)OpenAI
1,463
1,454–1,472
$2 / $10
45 Gemini 2.5 ProGoogle
1,462
1,459–1,465
$1.25 / $10
46 Claude Sonnet 4.6Anthropic
1,461
1,458–1,464
$3 / $15
47 GPT-5.6 Luna (extra-high reasoning)OpenAI
1,460
1,457–1,464
$0.20 / $1.20
48 Claude Opus 4.5Anthropic
1,459
1,456–1,462
$5 / $25
48 Claude Opus 4.5 (high reasoning, 32k budget)Anthropic
1,459
1,456–1,463
$5 / $25
48 GPT-5.1 (high reasoning)OpenAI
1,459
1,455–1,462
$1.25 / $10
51 MiMo-V2.6-FlashXiaomi
1,457
1,450–1,464
$0.14 / $0.28
51 Grok 4.20 Multi-Agent Beta (0309)xAI
1,457
1,454–1,460
–
53 Kimi K2.6Moonshot AI
1,456
1,452–1,460
$0.95 / $4
53 GLM-5.1Z.ai
1,456
1,453–1,459
$1.38 / $4.40
53 ERNIE 5.1Baidu
1,456
1,452–1,460
–
53 Grok 4.20 Beta (0309, reasoning)xAI
1,456
1,453–1,459
–
57 DeepSeek-V4-Pro (0423)DeepSeek
1,455
1,452–1,458
$1.42 / $2.83
58 DeepSeek-V4-Pro (0813, high reasoning)DeepSeek
1,454
1,448–1,459
$1.32 / $3.96
59 Qwen3.6-Max-PreviewAlibaba
1,453
1,445–1,460
$1.03 / $6.16
59 Qwen3.7-PlusAlibaba
1,453
1,449–1,456
$0.32 / $1.28
61 Grok 4.20 Beta 1xAI
1,452
1,448–1,457
–
61 Step 5 PreviewStepFun
1,452
1,442–1,461
–
61 Claude Sonnet 5 (high reasoning)Anthropic
1,452
1,448–1,455
$2 / $10
61 GLM-5Z.ai
1,452
1,448–1,456
$0.95 / $2.55
65 Nova Experimental Chat (2026-02-10)Amazon
1,451
1,443–1,460
–
65 InklingThinking Machines
1,451
1,448–1,455
$0.95 / $4.05
65 Gemini 3 Flash Preview (minimal reasoning)Google
1,451
1,449–1,454
$0.50 / $3
65 GPT-5.2 Chat (2026-02-10)OpenAI
1,451
1,447–1,455
–
69 Gemma 4 31BGoogle
1,450
1,443–1,457
$0.14 / $0.40
70 Claude Sonnet 4.5Anthropic
1,449
1,446–1,451
$3 / $15
70 Grok 4.6 (high reasoning)xAI
1,449
1,444–1,453
$2 / $6
72 DeepSeek-V4-Pro (0423, high reasoning)DeepSeek
1,448
1,444–1,451
$1.42 / $2.83
73 Gemini 3.5 Flash-LiteGoogle
1,447
1,444–1,451
$0.30 / $2.50
73 GPT-5.4 mini (high reasoning)OpenAI
1,447
1,444–1,450
$0.75 / $4.50
73 GLM-4.6Z.ai
1,447
1,443–1,451
$0.50 / $2
73 Claude Sonnet 4.5 (high reasoning, 32k budget)Anthropic
1,447
1,444–1,449
$3 / $15
77 DeepSeek-V3.2-Exp (reasoning on)DeepSeek
1,446
1,435–1,457
$0.27 / $0.41
78 Hy3Tencent
1,445
1,440–1,451
$0.14 / $0.58
78 ERNIE 5.0 (0110)Baidu
1,445
1,442–1,449
–
78 Kimi K2.5 (reasoning on)Moonshot AI
1,445
1,442–1,448
$0.57 / $2.85
78 Qwen3.5-397B-A17BAlibaba
1,445
1,442–1,447
$0.55 / $3.50
78 Gemma 4 26B A4BGoogle
1,445
1,438–1,452
$0.10 / $0.30
78 GPT-5.1OpenAI
1,445
1,441–1,448
$1.25 / $10
84 GLM-4.7Z.ai
1,444
1,438–1,450
$0.54 / $1.98
84 ChatGPT-4o (2025-03-26)OpenAI
1,444
1,441–1,447
–
84 GPT-5.5 InstantOpenAI
1,444
1,439–1,448
–
87 MiMo-V2-ProXiaomi
1,443
1,439–1,448
–
88 GPT-5.2OpenAI
1,442
1,440–1,445
$1.75 / $14
88 ERNIE 5.0 Preview (1203)Baidu
1,442
1,436–1,448
–
88 Qwen3-Max-PreviewAlibaba
1,442
1,435–1,448
–
88 GPT-5.2 (high reasoning)OpenAI
1,442
1,438–1,445
$1.75 / $14
92 GLM-5V-TurboZ.ai
1,440
1,435–1,446
$1.20 / $4
92 ERNIE 5.0 Preview (1022)Baidu
1,440
1,431–1,449
–
94 DeepSeek-V4-Flash (0423)DeepSeek
1,439
1,436–1,442
$0.14 / $0.28
94 MiMo-V2.5Xiaomi
1,439
1,435–1,442
$0.17 / $0.34
96 Qwen3.8-27BAlibaba
1,438
1,434–1,443
$0.50 / $3
96 Qwen3.6-PlusAlibaba
1,438
1,434–1,441
$0.33 / $1.95
98 DeepSeek-V3.2DeepSeek
1,437
1,434–1,440
$0.30 / $0.96
98 Gemini 2.5 FlashGoogle
1,437
1,434–1,439
$0.30 / $2.50
100 DeepSeek-V3.2-ExpDeepSeek
1,436
1,430–1,442
$0.27 / $0.41
100 MiMo-V2-OmniXiaomi
1,436
1,431–1,441
–
102 Claude Opus 4.1Anthropic
1,435
1,432–1,439
$15 / $75
103 MiniMax-M3MiniMax
1,434
1,431–1,437
$0.30 / $1.20
103 GPT-6 Sol (max reasoning)OpenAI
1,434
1,428–1,440
$2 / $10
103 Grok 4.1 ThinkingxAI
1,434
1,431–1,437
–
103 Mistral Large 3Mistral AI
1,434
1,431–1,436
$0.50 / $1.50
103 DeepSeek-V4-Flash (0423, high reasoning)DeepSeek
1,434
1,430–1,437
$0.14 / $0.28
108 Claude Opus 4.1 (16k reasoning budget)Anthropic
1,433
1,429–1,437
$15 / $75
108 Gemini 3.1 Flash-Lite PreviewGoogle
1,433
1,430–1,436
$0.25 / $1.50
108 DeepSeek-V3.2 (reasoning on)DeepSeek
1,433
1,429–1,436
$0.30 / $0.96
111 Qwen3-235B-A22B-Instruct-2507Alibaba
1,431
1,429–1,434
$0.15 / $0.75
111 Nemotron 3 Ultra 550B A55B (NVFP4)NVIDIA
1,431
1,425–1,437
–
111 Grok 4.1xAI
1,431
1,428–1,434
–
111 Mistral Medium 3.5Mistral AI
1,431
1,425–1,436
$1.50 / $7.50
115 GPT-6 Luna (max reasoning)OpenAI
1,430
1,424–1,436
$0.10 / $0.50
116 Kimi K2.5 (no reasoning)Moonshot AI
1,429
1,423–1,435
$0.57 / $2.85
116 Mistral Medium 3.1Mistral AI
1,429
1,426–1,432
$0.40 / $2
116 LongCat-Flash-Chat (2602, experimental)Meituan
1,429
1,425–1,433
–
119 Grok 4.7 (extra-high reasoning)xAI
1,428
1,421–1,435
$2 / $6
119 Grok 4.3xAI
1,428
1,425–1,431
$1.25 / $2.50
119 Qwen3.5-122B-A10BAlibaba
1,428
1,424–1,431
$0.26 / $2.08
122 Inkling SmallThinking Machines
1,426
1,422–1,430
$0.45 / $1.20
123 Gemini 2.5 Flash Preview (09-2025)Google
1,425
1,420–1,429
–
124 Nova Experimental Chat (12-10)Amazon
1,424
1,415–1,434
–
125 Kimi K2 Thinking TurboMoonshot AI
1,423
1,420–1,426
–
126 MiMo-V2-Flash (no reasoning)Xiaomi
1,422
1,419–1,425
–
126 GPT-5 ChatOpenAI
1,422
1,415–1,429
–
126 MiniMax-M2.7MiniMax
1,422
1,419–1,425
$0.30 / $1.20
129 GPT-5 (high reasoning)OpenAI
1,421
1,414–1,428
$1.25 / $10
130 Qwen3.5-27BAlibaba
1,420
1,416–1,424
$0.27 / $2.16
131 Dola-Seed-2.0-ProByteDance
1,419
1,416–1,422
–
131 Qwen3-Next-80B-A3B-InstructAlibaba
1,419
1,412–1,425
$0.10 / $1.10
131 GPT-5.3 ChatOpenAI
1,419
1,415–1,422
–
134 Grok 4 (0709)xAI
1,418
1,412–1,424
–
134 GPT-5.4 nano (high reasoning)OpenAI
1,418
1,415–1,421
$0.20 / $1.25
134 Claude Haiku 4.5Anthropic
1,418
1,416–1,420
$1 / $5
137 Grok 4 Fast (reasoning)xAI
1,417
1,411–1,423
–
137 Step 3.5 FlashStepFun
1,417
1,414–1,420
$0.10 / $0.30
139 Nova Experimental Chat (11-10)Amazon
1,415
1,411–1,419
–
139 Qwen3-VL-235B-A22B-InstructAlibaba
1,415
1,397–1,432
$0.30 / $1.50
141 Qwen3.5-FlashAlibaba
1,414
1,411–1,417
$0.065 / $0.26
142 Grok 4.1 Fast (reasoning)xAI
1,413
1,410–1,416
–
143 Hy3 PreviewTencent
1,412
1,405–1,419
$0.18 / $0.60
144 MiniMax-M2.1 PreviewMiniMax
1,411
1,406–1,416
–
145 MiMo-V2-Flash (reasoning on)Xiaomi
1,410
1,405–1,416
–
145 Solar Pro 4Upstage
1,410
1,405–1,415
$0.09 / $0.36
147 GPT-4.1OpenAI
1,408
1,402–1,415
$2 / $8
148 Qwen3.5-35B-A3BAlibaba
1,407
1,404–1,411
$0.16 / $1.30
148 Gemini 2.5 Flash-Lite Preview (09-2025, no reasoning)Google
1,407
1,404–1,411
–
150 o3OpenAI
1,405
1,398–1,411
$2 / $8
151 Kimi K2 (0905)Moonshot AI
1,403
1,389–1,418
$0.60 / $2.50
151 Nova Experimental Chat (2026-01-10)Amazon
1,403
1,394–1,411
–
153 Muse GlimmerMeta
1,402
1,394–1,410
–
154 Qwen3-Coder-480B-A35BAlibaba
1,401
1,383–1,419
$0.35 / $1.50
155 Nova Experimental Chat (10-20)Amazon
1,399
1,393–1,405
–
156 GLM-4.5-AirZ.ai
1,395
1,388–1,402
$0.14 / $0.86
157 GPT-5 mini (high reasoning)OpenAI
1,394
1,387–1,401
$0.25 / $2
158 GLM-4.6VZ.ai
1,392
1,381–1,402
$0.30 / $0.90
159 Nemotron 3 Super 120B A12BNVIDIA
1,390
1,383–1,397
$0.085 / $0.40
160 MiniMax-M2.5MiniMax
1,386
1,382–1,389
$0.30 / $1.20
161 gpt-oss-120bOpenAI
1,385
1,378–1,391
$0.15 / $0.60
162 Nova 2 LiteAmazon
1,380
1,374–1,386
$0.30 / $2.50
162 Gemma 3 27BGoogle
1,380
1,369–1,391
$0.12 / $0.20
164 Granite 4.2 30BIBM
1,375
1,366–1,384
–
165 INTELLECT-3Prime Intellect
1,373
1,365–1,381
–
165 Trinity Large PreviewArcee AI
1,373
1,369–1,376
–
167 Trinity Large ThinkingArcee AI
1,371
1,367–1,375
$0.25 / $0.80
168 GLM-4.7-FlashZ.ai
1,370
1,364–1,376
$0.06 / $0.40
168 MiniMax-M1MiniMax
1,370
1,359–1,381
$0.40 / $2.20
170 Mercury 2Inception
1,369
1,359–1,378
$0.25 / $0.75
171 o4-miniOpenAI
1,368
1,358–1,378
$1.10 / $4.40
172 Command ACohere
1,363
1,357–1,370
$2.50 / $10
173 Nemotron 3.5 Lightning 30B A3B (NVFP4)NVIDIA
1,362
1,357–1,368
–
173 Nemotron 3 Nano 30B A3BNVIDIA
1,362
1,357–1,367
$0.05 / $0.20
175 MiniMax-M2MiniMax
1,360
1,353–1,367
$0.30 / $1.20
176 Olmo 3.1 32B InstructAi2
1,342
1,336–1,348
–
176 Granite 4.2 8BIBM
1,342
1,332–1,352
$0.06 / $0.25
178 Granite 4.2 3BIBM
1,325
1,315–1,335
–
179 Olmo 3 32B ThinkAi2
1,319
1,312–1,327
–
180 Granite 4.1 8BIBM
1,311
1,302–1,320
–
181 MercuryInception
1,305
1,292–1,317
–
182 Olmo 3.1 32B ThinkAi2
1,300
1,293–1,307
–

Swipe the table sideways for more columns.

Ranks follow the score as shown, so equal numbers share a rank. ≈ marks results whose 95% range overlaps the leader's: they cannot be told apart from it. Results as published by Arena (formerly LMArena); we do not re-run them.

What it measures

Human preference combined with labels of whether each answer's checkable claims were true (factuality weighted 25% by default).

What it does not measure

Not an error rate: claims that cannot be checked on the web are skipped, and preference still carries most of the weight.

Source

Arena (formerly LMArena) · Methodology

Contains data from the Arena Leaderboard Dataset by Arena, licensed under CC BY 4.0. Licence: Creative Commons Attribution 4.0 International.