LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Compare AI models

Put two models in the arena: search, press A or B in the list below, or take a suggested rival. The tally appears at once; the full comparison is one click away, and the address updates so you can share it.

No model yet. Search above, or press A on any model in the list below.

No model yet. Search above, press B in the list, or take a suggested rival.

Choose two models to compare.

Popular duels

The best-measured models at the top of the leaderboard, paired. The score is the boards each one wins where both have a result.

All 136 ranked models

Press A or B to put a model in the arena. Sort by coding index, overall index or price. The search above reaches every one of the 356 models we list, ranked or not.

Ranked models to put in the arena
Coding #ModelCoding indexOverallOutput $/MPick
1 Claude Opus 5.5Anthropic 92.2 57.6 $20.00
2 Claude Fable 5.1Anthropic 89.1 53.4 $50.00
3 Claude Sonnet 5.5Anthropic 88.9 56.0 $10.00
4 GPT-6 AstraOpenAI 88.7 52.7 $50.00
5 GPT-6.1 SolOpenAI 88.7 51.8 $10.00
6 Qwen3.8 FlashQwen 87.4 Not ranked $0.47
7 o3 ProOpenAI 84.9 21.9 $80.00
8 DeepSeek V4.1 Flash 1017DeepSeek 83.3 39.5 $0.60
9 Gemini 2.5 Pro Preview 06-05Google 83.1 Not ranked $10.00
10 GPT-6 SolOpenAI 82.8 47.6 $10.00
11 Claude Fable 5Anthropic 82.1 49.6 $50.00
12 Claude Opus 5Anthropic 81.8 50.8 $25.00
13 Gemini 4 ArgonGoogle 80.5 52.6 $10.00
14 Muse Spark 1.3Meta 79.7 48.1 $4.25
15 DeepSeek V4.1 FlashDeepSeek 77.2 24.7 $0.0112
16 GPT-5.6 SolOpenAI 76.7 47.0 $20.00
17 Grok 4.6xAI 76.4 44.3 $6.00
18 Claude Haiku 5.5Anthropic 75.9 43.4 $0.50
19 Gemini 3 Flash PreviewGoogle 75.8 26.3 $3.00
20 Grok 4.5xAI 75.5 38.8 $6.00
21 Grok 4.7xAI 75.0 46.4 $6.00
22 Qwen3.8 27BQwen 73.6 33.7 $2.20
23 GLM 5.3Z.ai 73.1 44.8 $1.40
24 MiMo-V2.6-ProXiaomi 72.6 46.3 $0.87
25 GPT-5OpenAI 72.2 23.0 $10.00
26 GPT-6 LunaOpenAI 71.4 38.1 $0.50
27 Step 5 PreviewStepFun 71.4 43.7 $2.70
28 R1 0528DeepSeek 71.4 13.1 $2.15
29 GLM 5.3 FlashZ.ai 71.0 41.8 $0.16
30 o3OpenAI 70.7 20.2 $8.00
31 Gemini 3.8 FlashGoogle 70.5 40.9 $4.125
32 DeepSeek V3DeepSeek 70.2 Not ranked $1.0287
33 Gemini 3.7 FlashGoogle 69.9 39.6 $3.75
34 GPT-5.6 TerraOpenAI 69.0 42.1 $12.00
35 o4 MiniOpenAI 68.6 16.7 $4.40
36 GPT-5.5OpenAI 67.8 38.4 $30.00
37 Claude Opus 4.6Anthropic 66.9 31.9 $25.00
38 Claude Opus 4.5Anthropic 66.8 29.1 $25.00
39 Claude Opus 4.8Anthropic 66.0 41.8 $25.00
40 Nemotron 3.5 Super VLNVIDIA 65.5 26.5 $0.50
41 Muse Spark 1.2Meta 65.1 39.6 $4.25
42 Kimi K2 0711Moonshot AI 64.7 12.7 $2.30
43 Muse WonderMeta 64.5 Not ranked $20.00
44 GLM 4.5Z.ai 64.2 12.8 $2.20
45 Claude Sonnet 5Anthropic 63.5 38.2 $10.00
46 Qwen3.8 Max (0902)Qwen 63.5 45.4 $6.00
47 Kimi K2 ThinkingMoonshot AI 63.4 22.0 $2.50
48 Muse Spark OpenMeta 62.1 Not ranked $4.25
49 MiMo-V2.6-FlashXiaomi 61.9 37.9 $0.28
50 Kimi K3Moonshot AI 61.8 43.6 $11.936
51 o1OpenAI 61.7 15.2 $60.00
52 Hy4 previewTencent 61.6 Not ranked $2.501
53 GPT-5.6 LunaOpenAI 61.5 37.3 $1.20
54 Qwen3 Coder 30B A3B InstructQwen 60.4 9.6 $0.28
55 GPT-5 MiniOpenAI 59.8 20.6 $2.00
56 GLM 5Z.ai 59.7 27.9 $1.92
57 MiniMax M2.5MiniMax 59.4 22.8 $0.95
58 Claude Sonnet 4.5Anthropic 59.1 20.7 $15.00
59 GPT-5.2OpenAI 58.9 30.4 $14.00
60 Kimi K2.5Moonshot AI 58.5 23.5 $2.50
61 Claude Sonnet 4.6Anthropic 57.8 30.1 $15.00
62 MiniMax M3MiniMax 57.8 29.2 $1.20
63 GLM 5.2Z.ai 57.7 33.7 $2.42
64 Mistral Large 4Mistral AI 55.3 38.4 $2.09
65 GPT-5.2-CodexOpenAI 55.1 28.5 $14.00
66 DeepSeek V3.2 ExpDeepSeek 55.0 16.6 $0.41
67 DeepSeek V4 Flash 0423DeepSeek 54.6 24.4 $0.182
68 DeepSeek V4 Pro 0813DeepSeek 54.6 36.0 $1.98
69 DeepSeek V3.2DeepSeek 54.4 21.5 $0.42
70 Devstral 2 2512Mistral AI 53.8 8.6 $2.00
71 GPT-5.1OpenAI 53.3 24.7 $10.00
72 GLM 4.6Z.ai 52.2 18.5 $2.20
73 o3 MiniOpenAI 52.1 12.5 $4.40
74 Claude Opus 4.7Anthropic 51.1 40.7 $25.00
75 GPT-5.1-CodexOpenAI 50.5 23.7 $10.00
76 Qwen3 Coder 480B A35BQwen 50.0 11.9 $1.00
77 Claude Haiku 4.5Anthropic 49.8 16.9 $5.00
78 T InklingThinking Machines 49.7 25.0 $4.05
79 Muse Spark 1.1Meta 48.9 33.7 $4.25
80 Gemini 3.6 FlashGoogle 48.3 34.0 $3.75
81 GPT-4.1OpenAI 46.5 12.7 $8.00
82 MiniMax M2MiniMax 45.3 18.6 $1.02
83 Qwen3.7 MaxQwen 45.1 29.5 $4.425
84 Kimi K2.6Moonshot AI 44.2 27.0 $3.41
85 GLM 5.1Z.ai 44.0 26.1 $3.036
86 Hy3Tencent 43.9 Not ranked $0.528
87 Gemini 3.5 FlashGoogle 42.8 33.6 $9.00
88 DeepSeek V3 0324DeepSeek 42.0 9.7 $1.14
89 Qwen3 32BQwen 40.0 7.3 $0.28
90 MiMo-V2.5-ProXiaomi 40.0 26.0 $0.87
91 Kimi K2.7 CodeMoonshot AI 39.1 25.8 $3.35
92 GPT-4oOpenAI 38.8 Not ranked $10.00
93 Gemma 4 31BGoogle 38.3 14.7 $0.40
94 GPT-5.4OpenAI 37.7 39.0 $15.00
95 DeepSeek V4 Flash Vision ExpDeepSeek 37.6 34.8 $0.6468
96 Qwen3.6 PlusQwen 37.4 27.0 $1.95
97 Gemini 2.5 ProGoogle 37.0 16.1 $10.00
98 DeepSeek V4 Pro 0423DeepSeek 35.3 30.4 $1.9105
99 Gemini 3.1 Pro PreviewGoogle 35.3 29.7 $12.00
100 GPT-5 NanoOpenAI 34.8 13.0 $0.40
101 gpt-oss-120bOpenAI 34.5 11.6 $0.60
102 MiMo-V2.5Xiaomi 34.0 21.8 $0.28
103 R Beam 1.0 501B A23BReflection 33.8 Not ranked $1.00
104 Gemini 3.5 Flash LiteGoogle 33.6 22.2 $2.50
105 GLM 4.7Z.ai 33.6 22.2 $1.98
106 Qwen2.5 Coder 32B InstructQwen 30.5 6.7 $1.00
107 T Inkling SmallThinking Machines 29.9 25.7 $1.20
108 GPT-5.3-CodexOpenAI 29.5 32.5 $14.00
109 GLM 5V TurboZ.ai 28.8 23.5 $4.00
110 Gemini 2.5 FlashGoogle 28.7 15.5 $2.50
111 Qwen3.5 397B A17BQwen 28.6 21.4 $2.34
112 GPT-4.1 MiniOpenAI 28.5 10.2 $1.60
113 MiniMax M2.7MiniMax 28.4 22.8 $1.20
114 GPT-5.4 MiniOpenAI 28.2 24.1 $4.50
115 Claude Opus 4.1Anthropic 27.2 22.8 $75.00
116 Solar Pro 4Upstage 24.4 28.2 $0.60
117 GPT-4o (2024-08-06)OpenAI 23.1 7.7 $10.00
118 Qwen3.5-122B-A10BQwen 22.9 17.7 $2.08
119 Gemma 4 26B A4BGoogle 22.8 16.7 $0.255
120 Qwen3.5-27BQwen 22.6 22.9 $2.16
121 Grok 4.3xAI 22.5 24.9 $2.50
122 GPT-4OpenAI 22.4 6.7 $60.00
123 Hy3 previewTencent 22.4 25.3 $0.60
124 GPT-4o (2024-11-20)OpenAI 18.2 8.4 $10.00
125 Llama 4 MaverickMeta Llama 18.1 9.3 $0.6525
126 Mistral Medium 3.5Mistral AI 9.2 14.2 $7.50
127 Llama 4 ScoutMeta Llama 9.1 6.5 $0.30
128 GPT-4.1 NanoOpenAI 8.9 7.8 $0.40
129 Gemini 3.1 Flash Lite PreviewGoogle 8.1 15.6 $1.50
130 Qwen3.5-35B-A3BQwen 7.7 19.3 $1.00
131 GPT-5.1-Codex-MiniOpenAI 6.2 20.4 $2.00
132 Qwen3.5-FlashQwen 6.2 Not ranked $0.26
133 Trinity Large ThinkingArcee AI 5.4 10.8 $0.80
134 Gemma 3 27BGoogle 4.9 4.9 $0.35
135 GPT-4o-mini (2024-07-18)OpenAI 3.6 Not ranked $0.60
136 Mercury 2Inception 0.0 10.8 $0.75