tokenstat
tokenstat

Model catalog

Benchmarks

Public scores, so you can compare models next to their prices. Arena Elo from free open daily snapshots on GitHub (text, code, vision, agent), plus a sparse Artificial Analysis subset OpenRouter embeds. One score set is cross-linked onto provider clones of the same model. Arena may score the same base model at different reasoning efforts, so those rows stay separate and link to the base model only when it exists in the catalog. The open dumps publish 20 models per Arena board (10 on agent), so a full board is short by design. Empty on a single board is a gap, not a ranking of zero.

226 scored rows on this board · 532 linked into the catalog · as of · Models · AI plans

#ModelScore
1
OpenAI: GPT-6 AstraOpenAI · gpt-6-astra
61AA intelligence
2
xAI: Grok 4.6xAI · grok-4.6 · high effort
61AA intelligence
3
Meta: Muse Spark 1.3Meta · muse-spark-1.3 · xhigh effort
61AA intelligence
4
Anthropic: Claude Opus 5.5Anthropic · claude-opus-5-5
57.6AA intelligence
5
Anthropic: Claude Sonnet 5.5 ThinkingAnthropic · claude-sonnet-5-5
56AA intelligence
6
Anthropic: Claude Fable 5.1Anthropic · claude-fable-5.1
53.4AA intelligence
7
OpenAI: GPT-6.1 SolOpenAI · gpt-6.1-sol
51.8AA intelligence
8
Anthropic: Claude Opus 5Anthropic · claude-opus-5
50.8AA intelligence
9
Anthropic: Claude Fable 5Anthropic · claude-fable-5
49.6AA intelligence
10
Meta: Muse Spark 1.3meta · muse-spark-1.3
48.1AA intelligence
11
OpenAI: GPT-6 SolOpenAI · gpt-6-sol
47.6AA intelligence
12
OpenAI: GPT-5.6 SolOpenAI · gpt-5.6-sol
47AA intelligence
13
xAI: Grok 4.7xAI · grok-4.7
46.4AA intelligence
14
MiMo V2.6 ProXiaomi · mimo-v2.6-pro
46.3AA intelligence
15
Qwen3.8 Max 0902Alibaba · qwen3.8-max-0902
45.4AA intelligence
16
Mistral: GLM-5.3z-ai · glm-5.3
44.8AA intelligence
17
xAI: Grok 4.6x-ai · grok-4.6
44.3AA intelligence
18
Moonshot: Kimi K3moonshotai · kimi-k3
43.6AA intelligence
19
Anthropic: Claude Haiku 5.5Anthropic · claude-haiku-5-5
43.4AA intelligence
20
OpenAI: GPT-5.6 Terraopenai · gpt-5.6-terra
42.1AA intelligence
21
Anthropic: Claude Opus 4.8 Thinkinganthropic · claude-opus-4.8
41.8AA intelligence
22
Z.ai: GLM-5.3-Flashz-ai · glm-5.3-flash
41.8AA intelligence
23
Ling 3.1 Flashinclusionai · ling-3.1-flash
41.1AA intelligence
24
Google: Gemini 3.8 FlashGoogle · gemini-3.8-flash
40.9AA intelligence
25
Anthropic: Claude 4.7 Opus ThinkingAnthropic · claude-opus-4-7
40.7AA intelligence
26
Qwen3.8 2.4T A95Bqwen · qwen3.8-2.4t-a95b
39.9AA intelligence
27
Google: Gemini 3.7 Flashgoogle · gemini-3.7-flash
39.6AA intelligence
28
Meta: Muse Spark 1.2meta · muse-spark-1.2
39.6AA intelligence
29
DeepSeek: V4.1 FlashDeepSeek · deepseek-v4.1-flash
39.5AA intelligence
30
OpenAI: GPT-5.4OpenAI · gpt-5.4
39AA intelligence
31
xAI: Grok 4.5xAI · grok-4.5
38.8AA intelligence
32
OpenAI: GPT-5.5OpenAI · gpt-5.5
38.4AA intelligence
33
Anthropic: Claude Sonnet 5 Thinkinganthropic · claude-sonnet-5
38.2AA intelligence
34
OpenAI: GPT-6 LunaOpenAI · gpt-6-luna
38.1AA intelligence
35
MiMo V2.6 FlashXiaomi · mimo-v2.6-flash
37.9AA intelligence
36
OpenAI: GPT-5.6 Lunaopenai · gpt-5.6-luna
37.3AA intelligence
37
DeepSeek: V4 Pro 0813DeepSeek · deepseek-v4-pro-0813
36AA intelligence
38
DeepSeek: V4 Flash Vision Expdeepseek · deepseek-v4-flash-vision-exp
34.8AA intelligence
39
DeepSeek: V4 Flash 0731deepseek · deepseek-v4-flash-0731
34.3AA intelligence
40
Google: Gemini 3.6 Flashgoogle · gemini-3.6-flash
34AA intelligence
41
Mistral: GLM-5.2z-ai · glm-5.2
33.7AA intelligence
42
Meta: Muse Spark 1.1Meta · muse-spark-1.1
33.7AA intelligence
43
Qwen3.8 27Bqwen · qwen3.8-27b
33.7AA intelligence
44
Google: Gemini 3.5 Flashgoogle · gemini-3.5-flash
33.6AA intelligence
45
OpenAI: GPT-5.3 CodexOpenAI · gpt-5.3-codex
32.5AA intelligence
46
Anthropic: Claude 4.6 Opus ThinkingAnthropic · claude-opus-4.6
31.9AA intelligence
47
DeepSeek: V4 Prodeepseek · deepseek-v4-pro
30.4AA intelligence
48
OpenAI: GPT-5.2OpenAI · gpt-5.2
30.4AA intelligence
49
Anthropic: Claude Sonnet 4.6 Thinkinganthropic · claude-sonnet-4.6
30.1AA intelligence
50
Google: Gemini 3.1 Pro PreviewGoogle · gemini-3.1-pro-preview
29.7AA intelligence
51
Qwen3.7 Maxqwen · qwen3.7-max
29.5AA intelligence
52
MiniMax: M3minimax · minimax-m3
29.2AA intelligence
53
Anthropic: Claude 4.5 Opus Thinkinganthropic · claude-opus-4.5
29.1AA intelligence
54
OpenAI: GPT-5.2 CodexOpenAI · gpt-5.2-codex
28.5AA intelligence
55
Qwen3.6 Max Previewqwen · qwen3.6-max-preview
28.4AA intelligence
56
Solar Pro 4upstage · solar-pro4
28.2AA intelligence
57
Alibaba: GLM-5z-ai · glm-5
27.9AA intelligence
58
xAI: Grok Build 0.1x-ai · grok-build-0.1
27.2AA intelligence
59
Moonshot: Kimi K2.6moonshotai · kimi-k2.6
27AA intelligence
60
Qwen3.6 Plusqwen · qwen3.6-plus
27AA intelligence
61
Z.ai: zai-org/glm-5-turboz-ai · glm-5-turbo
26.6AA intelligence
62
Google: Gemini 3 Flash Previewgoogle · gemini-3-flash-preview
26.3AA intelligence
63
Z.ai: GLM-5.1z-ai · glm-5.1
26.1AA intelligence
64
MiMo V2.5 Pro Thinkingxiaomi · mimo-v2.5-pro
26AA intelligence
65
Moonshot: Kimi K2.7 Codemoonshotai · kimi-k2.7-code
25.8AA intelligence
66
25.7AA intelligence
67
Inkling Smallthinkingmachines · inkling-small
25.7AA intelligence
68
Hy3 Previewtencent · hy3-preview
25.3AA intelligence
69
MiMo V2.5 Thinkingxiaomi · mimo-v2.5
25.2AA intelligence
70
Qwen3.7 Plusqwen · qwen3.7-plus
25.2AA intelligence
71
NVIDIA: Inkling Thinkingthinkingmachines · inkling
25AA intelligence
72
xAI: Grok 4.3x-ai · grok-4.3
24.9AA intelligence
73
OpenAI: GPT-5.1openai · gpt-5.1
24.7AA intelligence
74
Ling 3.0 Flash VLinclusionai · ling-3.0-flash-vl
24.6AA intelligence
75
DeepSeek: V4 Flashdeepseek · deepseek-v4-flash
24.4AA intelligence
76
OpenAI: GPT-5.4 Miniopenai · gpt-5.4-mini
24.1AA intelligence
77
Solar Mini 4upstage · solar-mini4
24.1AA intelligence
78
OpenAI: GPT-5.1 Codexopenai · gpt-5.1-codex
23.7AA intelligence
79
Z.ai: GLM-5V-Turboz-ai · glm-5v-turbo
23.5AA intelligence
80
Moonshot: Kimi K2.5moonshotai · kimi-k2.5
23.5AA intelligence
81
OpenAI: GPT-5openai · gpt-5
23AA intelligence
82
NVIDIA: Nemotron Ultranvidia · nemotron-3-ultra-550b-a55b
22.9AA intelligence
83
Qwen3.5 27Bqwen · qwen3.5-27b
22.9AA intelligence
84
Anthropic: Claude Opus 4.1anthropic · claude-opus-4.1
22.8AA intelligence
85
MiniMax: M2.5minimax · minimax-m2.5
22.8AA intelligence
86
MiniMax: M2.7minimax · minimax-m2.7
22.8AA intelligence
87
Ling 3.0 Flash Fininclusionai · ling-3.0-flash-fin
22.6AA intelligence
88
Google: Gemini 3.5 Flash-Litegoogle · gemini-3.5-flash-lite
22.2AA intelligence
89
Z.ai: GLM-4.7z-ai · glm-4.7
22.2AA intelligence
90
Moonshot: Kimi K2 0711moonshotai · kimi-k2-thinking
22AA intelligence
91
OpenAI: o3 Proopenai · o3-pro
21.9AA intelligence
92
DeepSeek: V3.2deepseek · deepseek-v3.2
21.5AA intelligence
93
Qwen3.5 397B-A17Bqwen · qwen3.5-397b-a17b
21.4AA intelligence
94
Qwen3.6 27Bqwen · qwen3.6-27b
21.4AA intelligence
95
Qwen: 3 Max Thinkingqwen · qwen3-max-thinking
21.3AA intelligence
96
MiniMax: M2.1minimax · minimax-m2.1
20.9AA intelligence
97
Anthropic: Claude Sonnet 4.5 Thinkinganthropic · claude-sonnet-4.5
20.7AA intelligence
98
OpenAI: GPT-5.4 Nanoopenai · gpt-5.4-nano
20.7AA intelligence
99
OpenAI: GPT-5 Miniopenai · gpt-5-mini
20.6AA intelligence
100
OpenAI: GPT-5.1 Codex Miniopenai · gpt-5.1-codex-mini
20.4AA intelligence
101
OpenAI: o3openai · o3
20.2AA intelligence
102
Ling 3.0 Flashinclusionai · ling-3.0-flash
20.1AA intelligence
103
NVIDIA: Step 3.7 Flashstepfun · step-3.7-flash
19.5AA intelligence
104
Qwen3.5 35B-A3Bqwen · qwen3.5-35b-a3b
19.3AA intelligence
105
LongCat 2.0meituan · longcat-2.0
19.1AA intelligence
106
Anthropic: Claude Sonnet 4anthropic · claude-sonnet-4
18.9AA intelligence
107
MiniMax: M2minimax · minimax-m2
18.6AA intelligence
108
Z.ai: GLM-4.6z-ai · glm-4.6
18.5AA intelligence
109
Qwen3.6 35B-A3Bqwen · qwen3.6-35b-a3b
18.2AA intelligence
110
Qwen3.5 122B-A10Bqwen · qwen3.5-122b-a10b
17.7AA intelligence
111
Meta: Muse Glimmer 30Bmeta · muse-glimmer-30b
17.5AA intelligence
112
NVIDIA: Step 3.5 Flashstepfun · step-3.5-flash
17AA intelligence
113
Anthropic: Claude Haiku 4.5 ThinkingAnthropic · claude-haiku-4.5
16.9AA intelligence
114
Google: Gemma 4 26B A4Bgoogle · gemma-4-26b-a4b-it
16.7AA intelligence
115
OpenAI: o4 Miniopenai · o4-mini
16.7AA intelligence
116
DeepSeek: V3.2 Expdeepseek · deepseek-v3.2-exp
16.6AA intelligence
117
Google: Gemini 2.5 ProGoogle · gemini-2.5-pro
16.1AA intelligence
118
Google: Gemini 3.1 Flash Lite Previewgoogle · gemini-3.1-flash-lite-preview
15.6AA intelligence
119
Qwen: 3 Max Thinkingqwen · qwen3-max
15.6AA intelligence
120
Google: Gemini 2.5 FlashGoogle · gemini-2.5-flash
15.5AA intelligence
121
Moonshot: Kimi K2 0905moonshotai · kimi-k2-0905
15.3AA intelligence
122
OpenAI: o1openai · o1
15.2AA intelligence
123
Z.ai: GLM-4.7-Flashz-ai · glm-4.7-flash
14.9AA intelligence
124
DeepSeek: V3.1 Terminusdeepseek · deepseek-v3.1-terminus
14.8AA intelligence
125
Google: Gemma 4 31Bgoogle · gemma-4-31b-it
14.7AA intelligence
126
Mistral: Medium 3.5mistralai · mistral-medium-3-5
14.2AA intelligence
127
Mercury 2inception · mercury-2
13.8AA intelligence
128
DeepSeek: V3.1deepseek · deepseek-chat-v3.1
13.7AA intelligence
129
Amazon: Nova 2 Liteamazon · nova-2-lite-v1
13.4AA intelligence
130
Qwen3-VL 235B-A22Bqwen · qwen3-vl-235b-a22b-thinking
13.4AA intelligence
131
Qwen3.5 9Bqwen · qwen3.5-9b
13.3AA intelligence
132
Cohere: Command Acohere · command-a
13.1AA intelligence
133
DeepSeek: R1 0528deepseek · deepseek-r1-0528
13.1AA intelligence
134
OpenAI: GPT-5 Nanoopenai · gpt-5-nano
13AA intelligence
135
NVIDIA: Nemotron 3.5 Lightningnvidia · nemotron-3.5-lightning
12.9AA intelligence
136
Z.ai: GLM-4.5z-ai · glm-4.5
12.8AA intelligence
137
NVIDIA: Nemotron 3 Super 120B A12Bnvidia · nemotron-3-super-120b-a12b
12.8AA intelligence
138
OpenAI: GPT-4.1openai · gpt-4.1
12.7AA intelligence
139
Moonshot: Kimi K2 0711moonshotai · kimi-k2
12.7AA intelligence
140
Qwen3 235B A22B Thinking 2507qwen · qwen3-235b-a22b-thinking-2507
12.7AA intelligence
141
OpenAI: o3 Miniopenai · o3-mini
12.5AA intelligence
142
OpenAI: o1-proopenai · o1-pro
12.4AA intelligence
143
Mercury 2.5inception · mercury-2.5
12.3AA intelligence
144
Qwen3 235B A22B Instruct 2507qwen · qwen3-235b-a22b-2507
12AA intelligence
145
11.9AA intelligence
146
Qwen3 VL 32B Instructqwen · qwen3-vl-32b-instruct
11.9AA intelligence
147
Perplexity: Sonar Reasoning Properplexity · sonar-reasoning-pro
11.8AA intelligence
148
MiniMax: M1minimax · minimax-m1
11.7AA intelligence
149
OpenAI: gpt-oss-120bopenai · gpt-oss-120b
11.6AA intelligence
150
DeepSeek: R1deepseek · deepseek-r1
11.4AA intelligence
151
Mistral: Small 4mistralai · mistral-small-2603
11.3AA intelligence
152
Z.ai: GLM-4.6Vz-ai · glm-4.6v
11.2AA intelligence
153
11.2AA intelligence
154
Z.ai: GLM-4.5-Airz-ai · glm-4.5-air
11.1AA intelligence
155
Granite 4.2 8Bibm-granite · granite-4.2-8b
11.1AA intelligence
156
OpenAI: o3 Mini Highopenai · o3-mini-high
11AA intelligence
157
Trinity Large Thinkingarcee-ai · trinity-large-thinking
10.8AA intelligence
158
Google: Gemini 2.5 Flash-Litegoogle · gemini-2.5-flash-lite
10.4AA intelligence
159
NVIDIA: Nemotron 3 Nano Omni 30B A3B Reasoningnvidia · nemotron-3-nano-omni-30b-a3b-reasoning
10.3AA intelligence
160
OpenAI: GPT-4.1 Miniopenai · gpt-4.1-mini
10.2AA intelligence
161
OpenAI: GPT OSS 20Bopenai · gpt-oss-20b
10AA intelligence
162
Meta: Llama 4 Maverickmeta-llama · llama-4-maverick
10AA intelligence
163
Cohere: North Mini Codecohere · north-mini-code
9.9AA intelligence
164
Qwen3 VL 235B A22B Instructqwen · qwen3-vl-235b-a22b-instruct
9.9AA intelligence
165
Qwen3 30B A3B Thinking 2507qwen · qwen3-30b-a3b-thinking-2507
9.8AA intelligence
166
DeepSeek: V3 0324deepseek · deepseek-chat-v3-0324
9.7AA intelligence
167
Qwen3-Coder 30B-A3B Instructqwen · qwen3-coder-30b-a3b-instruct
9.6AA intelligence
168
Qwen3-Next 80B-A3B Instructqwen · qwen3-next-80b-a3b-instruct
9.6AA intelligence
169
Qwen3 235B A22B Thinking 2507qwen · qwen3-235b-a22b
9.5AA intelligence
170
Qwen3-VL 30B-A3Bqwen · qwen3-vl-30b-a3b-thinking
9.5AA intelligence
171
Mistral: Large 3mistralai · mistral-large-2512
9.3AA intelligence
172
Mistral: Medium 3.1mistralai · mistral-medium-3.1
9.2AA intelligence
173
Amazon: Nova Premier 1.0amazon · nova-premier-v1
9.2AA intelligence
174
Qwen3 Coder Nextqwen · qwen3-coder-next
9.2AA intelligence
175
Mistral: Medium 3mistralai · mistral-medium-3
9AA intelligence
176
NVIDIA: Nemotron 3 Nano 30B A3Bnvidia · nemotron-3-nano-30b-a3b
8.9AA intelligence
177
Mistral: Devstral 2mistralai · devstral-2512
8.6AA intelligence
178
Qwen3 32Bqwen · qwen3-32b
8.6AA intelligence
179
OpenAI: GPT-4o (2024-11-20)openai · gpt-4o-2024-11-20
8.4AA intelligence
180
LFM2.5 2.6Bliquid · lfm-2.5-2.6b
8.4AA intelligence
181
Qwen3 14Bqwen · qwen3-14b
8.2AA intelligence
182
Qwen3 VL 8B Thinkingqwen · qwen3-vl-8b-thinking
8.2AA intelligence
183
Meta: Llama 4 Scoutmeta-llama · llama-4-scout
8.1AA intelligence
184
Qwen3 VL 30B A3B Instructqwen · qwen3-vl-30b-a3b-instruct
7.9AA intelligence
185
OpenAI: GPT-4.1 Nanoopenai · gpt-4.1-nano
7.8AA intelligence
186
Solar Pro 3upstage · solar-pro-3
7.8AA intelligence
187
OpenAI: GPT-4o (2024-08-06)openai · gpt-4o-2024-08-06
7.7AA intelligence
188
Meta: Llama 3.3 70B Instructmeta-llama · llama-3.3-70b-instruct
7.7AA intelligence
189
Qwen2.5 72B Instructqwen · qwen-2.5-72b-instruct
7.7AA intelligence
190
Perplexity: Sonarperplexity · sonar
7.7AA intelligence
191
Z.ai: GLM-4.5Vz-ai · glm-4.5v
7.6AA intelligence
192
Mistral: Large 2407mistralai · mistral-large-2407
7.6AA intelligence
193
Qwen3 30B A3Bqwen · qwen3-30b-a3b
7.6AA intelligence
194
Perplexity: Sonar Properplexity · sonar-pro
7.6AA intelligence
195
Hermes 4 405Bnousresearch · hermes-4-405b
7.5AA intelligence
196
Qwen3 30B A3B Instruct 2507qwen · qwen3-30b-a3b-instruct-2507
7.5AA intelligence
197
Hermes 3 405B Instructnousresearch · hermes-3-llama-3.1-405b
7.4AA intelligence
198
OpenAI: GPT-4o (2024-05-13)openai · gpt-4o-2024-05-13
7.3AA intelligence
199
Qwen3 8Bqwen · qwen3-8b
7.3AA intelligence
200
Qwen3 VL 8B Instructqwen · qwen3-vl-8b-instruct
7.3AA intelligence
201
OpenAI: GPT-4 Turboopenai · gpt-4-turbo
7AA intelligence
202
Amazon: Nova Pro 1.0amazon · nova-pro-v1
7AA intelligence
203
Meta: Llama 3.1 8B Instructmeta-llama · llama-3.1-8b-instruct
6.9AA intelligence
204
OpenAI: GPT-4openai · gpt-4
6.7AA intelligence
205
OpenAI: GPT-4o-miniopenai · gpt-4o-mini
6.7AA intelligence
206
Hermes 3 70B Instructnousresearch · hermes-3-llama-3.1-70b
6.7AA intelligence
207
Mistral: Small 3mistralai · mistral-small-24b-instruct-2501
6.7AA intelligence
208
Amazon: Nova Lite 1.0amazon · nova-lite-v1
6.7AA intelligence
209
Qwen2.5 Coder 32B Instructqwen · qwen-2.5-coder-32b-instruct
6.7AA intelligence
210
Meta: Llama 3.1 70B Instructmeta-llama · llama-3.1-70b-instruct
6.6AA intelligence
211
Mistral: Sabamistralai · mistral-saba
6.5AA intelligence
212
Reka Flash 3rekaai · reka-flash-3
6.4AA intelligence
213
Mistral: Ministral 3 14B 2512mistralai · ministral-14b-2512
6AA intelligence
214
Amazon: Nova Micro 1.0amazon · nova-micro-v1
5.9AA intelligence
215
Phi 4microsoft · phi-4
5.9AA intelligence
216
Mistral: Largemistralai · mistral-large
5.8AA intelligence
217
Meta: Llama 3.2 3B Instructmeta-llama · llama-3.2-3b-instruct
5.7AA intelligence
218
Mistral: Mixtral 8x22B Instructmistralai · mixtral-8x22b-instruct
5.7AA intelligence
219
OpenAI: GPT-3.5 Turboopenai · gpt-3.5-turbo
5.5AA intelligence
220
Mistral: Ministral 3 8B 2512mistralai · ministral-8b-2512
5.5AA intelligence
221
Granite 4.0 H Microibm-granite · granite-4.0-h-micro
5.1AA intelligence
222
Google: Gemma 3 27Bgoogle · gemma-3-27b-it
4.9AA intelligence
223
Google: Gemma 3 4Bgoogle · gemma-3-4b-it
4.8AA intelligence
224
Meta: Llama 3.2 1B Instructmeta-llama · llama-3.2-1b-instruct
4.8AA intelligence
225
Mistral: Ministral 3 3B 2512mistralai · ministral-3b-2512
4.8AA intelligence
226
Google: Gemma 3 12Bgoogle · gemma-3-12b-it
3.8AA intelligence

Sources

Arena Elo from Arena AI, via open dumps by oolong-tea-2026. Artificial Analysis indices via OpenRouter (subset). Artificial Analysis for the indices themselves. Plus vendor-reported launch evals collected from announcements, analyst writeups, launch blogs, and community benchmarks. As of .

Turn benchmark scores into working sessions

Run agents in a local Git-enabled workspace, connect to another machine when needed, and track the sessions and tokens behind your work. See what your AI subscriptions covered.

macOSDownloadWindowsPreviewCLImacOS · Linux · WindowsApp StoreDownloadGoogle PlayDownload