Translate
Independent model intelligence

Find the right AI model,
not just the loudest one.

Compare current model capability, context, modalities, public preference and API economics in one continuously refreshed decision surface.

LMArena models.dev OpenRouter Artificial Analysis when available
Ranked now131of 170 tracked models
Public evidence155verified benchmark results
Evaluation map89reviewed upstream sources
Builders / multimodal20 / 107providers · rich-input models
Leaders right now

Overall capability

Direct public data · prices never affect capability rank
01
GoogleGemini 4 Argon
Overall capability92.3
1M context$10 / 1M out
02
AnthropicClaude Opus 5.5
Overall capability85.7
1M context$20 / 1M out
03
AnthropicClaude Fable 5.1
Overall capability84.0
1M context$50 / 1M out
170 matching models · select up to four to compare
Overall capability. A score of 50 is the current reference-set average. Price and speed are shown for comparison but never affect rank.
Full ranking

Overall capability

Open a model for verified evidence, specifications and related releases
RankModelCapabilityContextAPI pricingEvidenceCompare
01—Gemini 4 ArgonGoogle · geminiMultimodalReasoningTools92.3Overall capability1MLaunched 2026-10-13$2 in$10 out1 public result1 source · 3% coverage
02—Claude Opus 5.5Anthropic · claude-opusMultimodalReasoningTools85.7Overall capability1MLaunched 2026-09-22$4 in$20 out1 public result1 source · 3% coverage
03—Claude Fable 5.1Anthropic · claude-fableMultimodalReasoningTools84.0Overall capability1MLaunched 2026-09-01$10 in$50 out1 public result1 source · 3% coverage
04—Claude Opus 5Anthropic · claude-opusMultimodalReasoningTools80.4Overall capability1MLaunched 2026-07-24$5 in$25 out1 public result1 source · 3% coverage
05—Muse WonderMeta · museMultimodalReasoningTools79.7Overall capability1MLaunched 2026-10-12$4 in$20 out1 public result1 source · 3% coverage
06—Gemini 3.8 FlashGoogle · gemini-flashMultimodalReasoningTools78.9Overall capability1MLaunched 2026-09-02$0.76 in$3.79 out1 public result1 source · 3% coverage
07—Claude Opus 4.6Anthropic · claude-opusMultimodalReasoningTools78.4Overall capability200kLaunched 2026-02-05$5 in$25 out1 public result1 source · 3% coverage
08—Claude Fable 5Anthropic · claude-fableMultimodalReasoningTools75.9Overall capability1MLaunched 2026-06-09$10 in$50 out1 public result1 source · 3% coverage
09—mimo-v2.6-proXiaomi · mimoMultimodalReasoningTools75.6Overall capability1MLaunched 2026-09-22$0.43 in$0.87 out1 public result1 source · 3% coverage
10—Muse Spark 1.3Meta · museMultimodalReasoningTools75.4Overall capability1MLaunched 2026-09-02$1.25 in$4.25 out1 public result1 source · 3% coverage
11—Gemini 3.7 FlashGoogle · gemini-flashMultimodalReasoningTools74.3Overall capability1MLaunched 2026-08-13$0.76 in$3.79 out1 public result1 source · 3% coverage
12—Muse Spark 1.2Meta · museMultimodalReasoningTools72.8Overall capability1MLaunched 2026-08-05$1.25 in$4.25 out1 public result1 source · 3% coverage
13—Claude Opus 4.7Anthropic · claude-opusMultimodalReasoningTools72.5Overall capability1MLaunched 2026-04-16$5 in$25 out1 public result1 source · 3% coverage
14—qwen3.8-maxAlibaba Qwen · qwenMultimodalToolsStructured72.5Overall capability256kLaunched 2026-08-03$1.65 in$4.95 out1 public result1 source · 3% coverage
15—gemini-3.5-flash-highGoogle · gemini-flashMultimodalReasoningTools72.2Overall capability1MLaunched 2026-05-19$1.52 in$9.09 out1 public result1 source · 3% coverage
162gemini-3.6-flash-highGoogle · gemini-flashMultimodalReasoningTools71.1Overall capability1MLaunched 2026-07-21$0.76 in$3.79 out1 public result1 source · 3% coverage
172Muse Spark 1.1Meta · museMultimodalReasoningTools70.6Overall capability1MLaunched 2026-04-08$1.25 in$4.25 out1 public result1 source · 3% coverage
182qwen3.7-max-previewAlibaba Qwen · qwenReasoningToolsStructured69.4Overall capability256kLaunched 2026-05-21$2.5 in$7.5 out1 public result1 source · 3% coverage
192Kimi K3Moonshot AI · kimi-k3MultimodalReasoningTools69.2Overall capability1MLaunched 2026-07-16$2.85 in$14.25 out1 public result1 source · 3% coverage
202Muse SparkMeta · museMultimodalReasoningTools69.0Overall capability1MLaunched 2026-08-05$1.25 in$4.25 out1 public result1 source · 3% coverage
212glm-5.3-maxZhipu AI · glmReasoningToolsStructured67.9Overall capability1MLaunched 2026-08-14$0.9 in$4 out1 public result1 source · 3% coverage
222glm-5.3-flashZhipu AI · glm-flashMultimodalReasoningTools67.6Overall capability1MLaunched 2026-08-26$0.15 in$0.5 out1 public result1 source · 3% coverage
232claude-sonnet-5.5-xhighAnthropic · claude-sonnetMultimodalReasoningTools67.5Overall capability1MLaunched 2026-09-28$2 in$10 out1 public result1 source · 3% coverage
242glm-5.2-maxZhipu AI · glmReasoningToolsStructured67.5Overall capability1MLaunched 2026-06-13$0.75 in$2.4 out1 public result1 source · 3% coverage
253ernie-5.1Baidu · ernieReasoning66.5Overall capability119kLaunched 2026-05-10$0.75 in$3 out1 public result1 source · 3% coverage
263gpt-5.5OpenAI · gptMultimodalReasoningTools66.1Overall capability272kLaunched 2026-03-05$2.5 in$15 out1 public result1 source · 3% coverage
274deepseek-v4.1-flash-maxDeepSeek · deepseek-flashMultimodalReasoningTools64.5Overall capability1MLaunched 2026-09-10$0.2 in$0.6 out1 public result1 source · 3% coverage
285claude-sonnet-4-6Anthropic · claude-sonnetMultimodalReasoningTools62.5Overall capability200kLaunched 2026-02-17$3 in$15 out1 public result1 source · 3% coverage
296gpt-5.6-sol-xhighOpenAI · gpt-solMultimodalReasoningTools62.2Overall capability1.1MLaunched 2026-07-09$2 in$10 out1 public result1 source · 3% coverage
307mimo-v2.6-flashXiaomi · mimoMultimodalReasoningTools61.4Overall capability1MLaunched 2026-09-22$0.14 in$0.28 out1 public result1 source · 3% coverage
317qwen3.7-plusAlibaba Qwen · qwenMultimodalReasoningTools61.2Overall capability1MLaunched 2026-06-02$0.4 in$1.6 out1 public result1 source · 3% coverage
327claude-opus-4-8Anthropic · claude-opusMultimodalReasoningTools60.9Overall capability1MLaunched 2026-05-28$4.29 in$21.46 out1 public result1 source · 3% coverage
337gpt-5.4OpenAI · gptMultimodalReasoningTools60.2Overall capability1.1MLaunched 2026-03-05$2.5 in$15 out1 public result1 source · 3% coverage
347deepseek-v4-proDeepSeek · deepseek-thinkingReasoningToolsStructured59.8Overall capability1MLaunched 2026-04-24$1.3 in$2.6 out1 public result1 source · 3% coverage
357claude-opus-4-5-20251101Anthropic · claude-opusMultimodalReasoningTools59.7Overall capability200kLaunched 2025-11-24$5 in$25 out1 public result1 source · 3% coverage
367grok-4.20-beta-0309-reasoningxAI · grokMultimodalTools59.7Overall capability2MLaunched 2026-03-09$2 in$6 out1 public result1 source · 3% coverage
377grok-4.20-multi-agent-beta-0309xAI · grokMultimodalReasoningTools59.5Overall capability256kLaunched 2025-07-10$3 in$15 out1 public result1 source · 3% coverage
387amazon-nova-experimental-chat-26-02-10AmazonText58.6Overall capability—Launch date pending— in— out1 public result1 source · 3% coverage
397claude-opus-4-5-20251101-high-32kAnthropic · claude-opusMultimodalReasoningTools58.6Overall capability200kLaunched 2025-11-24$5 in$25 out1 public result1 source · 3% coverage
407dola-seed-2.0-proByteDance · seedReasoning58.6Overall capability131.1kLaunched 2026-03-28$0.5 in$3 out1 public result1 source · 3% coverage
417grok-4.5xAI · grokMultimodalReasoningTools58.5Overall capability500kLaunched 2026-07-08$2 in$6 out1 public result1 source · 3% coverage
427gpt-6.1-sol-maxOpenAI · gpt-solMultimodalReasoningTools58.4Overall capability1.1MLaunched 2026-09-29$2 in$10 out1 public result1 source · 3% coverage
437gpt-5.6-terra-xhighOpenAI · gpt-terraMultimodalReasoningTools58.3Overall capability1.1MLaunched 2026-07-09$2 in$12 out1 public result1 source · 3% coverage
44—qwen3.6-max-previewAlibaba Qwen · qwenText58.2Overall capability245.8kLaunched 2026-04-20$1.04 in$6.24 out1 public result1 source · 3% coverage
45—nvidia-nemotron-3-ultra-550b-a55b-nvfp4NVIDIA · nemotronReasoningToolsStructured57.2Overall capability1MLaunched 2026-06-04$0.5 in$2.5 out1 public result1 source · 3% coverage
46—grok-4.20-beta1xAI · grokMultimodalReasoningTools57.2Overall capability256kLaunched 2025-07-10$3 in$15 out1 public result1 source · 3% coverage
47—ernie-5.0-0110BaiduMultimodalReasoningTools57.2Overall capability128kLaunched 2026-01-22$0.84 in$3.37 out1 public result1 source · 3% coverage
48—gemma-4-31bGoogle · gemmaMultimodalReasoningTools56.5Overall capability262.1kLaunched 2026-04-02$0.1 in$0.45 out1 public result1 source · 3% coverage
49—gpt-6-astra-maxOpenAI · gpt-astraMultimodalReasoningTools56.4Overall capability1.1MLaunched 2026-09-04$10 in$50 out1 public result1 source · 3% coverage
50—gemini-3-flash (thinking-minimal)Google · gemini-flashMultimodalReasoningTools56.3Overall capability1MLaunched 2025-12-17$0.5 in$3 out1 public result1 source · 3% coverage
51—ernie-5.0-preview-1203BaiduMultimodalReasoningTools56.3Overall capability128kLaunched 2026-01-22$0.84 in$3.37 out1 public result1 source · 3% coverage
52—claude-sonnet-5-highAnthropic · claude-sonnetMultimodalReasoningTools56.2Overall capability1MLaunched 2026-06-30$2 in$10 out1 public result1 source · 3% coverage
53—inklingThinking Machines · lingMultimodalReasoningTools55.9Overall capability524.3kLaunched 2026-07-15$0.95 in$4.05 out1 public result1 source · 3% coverage
54—qwen3.8-27bAlibaba Qwen · qwenMultimodalReasoningTools55.6Overall capability262.1kLaunched 2026-08-14$0.2 in$2.5 out1 public result1 source · 3% coverage
55—glm-4.6Zhipu AI · glmReasoningToolsStructured55.3Overall capability202.8kLaunched 2025-09-30$0.5 in$2 out1 public result1 source · 3% coverage
56—claude-sonnet-4-5-20250929Anthropic · claude-sonnetMultimodalReasoningTools54.7Overall capability200kLaunched 2025-09-29$3 in$15 out1 public result1 source · 3% coverage
57—qwen3.5-397b-a17bAlibaba Qwen · qwenMultimodalReasoningTools54.4Overall capability262.1kLaunched 2026-02-01$0.45 in$3 out1 public result1 source · 3% coverage
58—glm-5v-turboZhipu AI · glmMultimodalReasoningTools54.4Overall capability200kLaunched 2026-04-01$1.2 in$4 out1 public result1 source · 3% coverage
59—qwen3.6-plusAlibaba Qwen · qwenMultimodalReasoningTools53.9Overall capability1MLaunched 2026-04-02$0.5 in$3 out1 public result1 source · 3% coverage
60—grok-4.1xAIMultimodalTools53.8Overall capability200kLaunched 2025-11-18$2 in$10 out1 public result1 source · 3% coverage
61—glm-4.7Zhipu AI · glmReasoningToolsStructured53.5Overall capability202.8kLaunched 2025-12-22$0.4 in$1.75 out1 public result1 source · 3% coverage
62—claude-sonnet-4-5-20250929-high-32kAnthropic · claude-sonnetMultimodalReasoningTools53.2Overall capability200kLaunched 2025-09-29$3 in$15 out1 public result1 source · 3% coverage
63—gemini-3.5-flash-liteGoogle · gemini-flash-liteMultimodalReasoningTools53.2Overall capability1MLaunched 2026-07-21$0.3 in$2.53 out1 public result1 source · 3% coverage
64—gemma-4-26b-a4bGoogle · gemmaMultimodalReasoningTools53.0Overall capability262.1kLaunched 2026-04-02$0.05 in$0.29 out1 public result1 source · 3% coverage
65—minimax-m3MiniMax · minimaxMultimodalReasoningTools52.7Overall capability524.3kLaunched 2026-06-01$0.28 in$1.1 out1 public result1 source · 3% coverage
66—deepseek-v4-flashDeepSeek · deepseek-flashReasoningToolsStructured52.1Overall capability1MLaunched 2026-04-24$0.09 in$0.18 out1 public result1 source · 3% coverage
67—gpt-5.6-luna-xhighOpenAI · gpt-lunaMultimodalReasoningTools51.6Overall capability1.1MLaunched 2026-07-09$0.2 in$1.2 out1 public result1 source · 3% coverage
68—mistral-large-4Mistral AI · mistral-largeMultimodalReasoningTools51.4Overall capability524.3kLaunched 2026-10-06$0.68 in$2.09 out1 public result1 source · 3% coverage
69—glm-4.5Zhipu AI · glmReasoningToolsStructured51.3Overall capability131.1kLaunched 2025-07-28$0.6 in$2.2 out1 public result1 source · 3% coverage
70—ernie-5.0-preview-1022BaiduMultimodalReasoningTools51.3Overall capability128kLaunched 2026-01-22$0.84 in$3.37 out1 public result1 source · 3% coverage
71—mistral-large-3Mistral AI · mistral-largeMultimodalOpen weights50.6Overall capability262.1kLaunched 2025-12-02$0.5 in$1.5 out1 public result1 source · 3% coverage
72—grok-4.6-highxAI · grokMultimodalReasoningTools50.5Overall capability500kLaunched 2026-08-12$2 in$6 out1 public result1 source · 3% coverage
73—deepseek-r1-0528DeepSeek · deepseekReasoningToolsStructured50.4Overall capability163.8kLaunched 2025-05-28$0.5 in$2.15 out1 public result1 source · 3% coverage
74—longcat-flash-chat-2602-expmeituanText50.0Overall capability131.1kLaunched 2025-11-05— in— out1 public result1 source · 3% coverage
75—grok-3-preview-02-24xAI · grokTools49.5Overall capability131.1kLaunched 2025-04-11$3 in$15 out1 public result1 source · 3% coverage
76—mimo-v2-omniXiaomi · mimoMultimodalReasoningTools48.7Overall capability265kLaunched 2026-03-18$0.4 in$2 out1 public result1 source · 3% coverage
77—longcat-flash-chatmeituanText48.4Overall capability131.1kLaunched 2025-11-05— in— out1 public result1 source · 3% coverage
78—gpt-5.1OpenAI · gptMultimodalReasoningTools48.3Overall capability400kLaunched 2025-11-13$1.25 in$10 out1 public result1 source · 3% coverage
79—mistral-medium-3.5Mistral AI · mistral-mediumMultimodalReasoningTools47.7Overall capability262.1kLaunched 2026-05-01$1.5 in$7.5 out1 public result1 source · 3% coverage
80—kimi-k2.5-instantMoonshot AI · kimi-thinkingReasoningToolsStructured47.4Overall capability262.1kLaunched 2025-11-06$0.6 in$2.5 out1 public result1 source · 3% coverage
81—qwen3-vl-235b-a22b-instructAlibaba Qwen · qwenMultimodalToolsStructured47.4Overall capability262.1kLaunched 2025-09-23$0.2 in$0.88 out1 public result1 source · 3% coverage
82—amazon-nova-experimental-chat-12-10AmazonText47.1Overall capability—Launch date pending— in— out1 public result1 source · 3% coverage
83—claude-opus-4-1-20250805-thinking-16kAnthropic · claude-opusMultimodalReasoningTools47.0Overall capability192.5kLaunched 2025-05-21$13 in$64 out1 public result1 source · 3% coverage
84—qwen3-235b-a22b-instruct-2507Alibaba Qwen · qwenToolsStructuredOpen weights47.0Overall capability262.1kLaunched 2025-07-21$0.09 in$0.55 out1 public result1 source · 3% coverage
85—gpt-5.5-instantOpenAIMultimodalReasoningTools47.0Overall capability400kLaunched 2026-05-05$5 in$30 out1 public result1 source · 3% coverage
86—claude-opus-4-1-20250805Anthropic · claude-opusMultimodalToolsStructured46.8Overall capability200kLaunched 2025-08-05$15 in$75 out1 public result1 source · 3% coverage
87—gpt-4.5-preview-2025-02-27OpenAI · gptMultimodalReasoningTools46.3Overall capability1.1MLaunched 2026-03-29$10 in$50 out1 public result1 source · 3% coverage
88—deepseek-v3.1-terminusDeepSeek · deepseekReasoningToolsStructured46.2Overall capability128kLaunched 2025-08-02$0.25 in$0.7 out1 public result1 source · 3% coverage
89—qwen3-next-80b-a3b-instructAlibaba Qwen · qwenToolsStructuredOpen weights46.2Overall capability262.1kLaunched 2025-09$0.09 in$1.1 out1 public result1 source · 3% coverage
90—gemini-3.1-flash-lite-previewGoogle · gemini-flash-liteMultimodalReasoningTools45.7Overall capability1MLaunched 2026-05-07$0.25 in$1.52 out1 public result1 source · 3% coverage
91—qwen3-235b-a22b-thinking-2507Alibaba Qwen · qwenReasoningTools45.4Overall capability128kLaunched 2025-07-25$0.45 in$3.5 out1 public result1 source · 3% coverage
92—amazon-nova-experimental-chat-11-10AmazonText45.4Overall capability—Launch date pending— in— out1 public result1 source · 3% coverage
93—qwen3-max-2025-09-23Alibaba QwenTools44.5Overall capability258kLaunched 2025-09-24$0.86 in$3.43 out1 public result1 source · 3% coverage
94—Inkling SmallThinking Machines · lingMultimodalReasoningTools44.4Overall capability524.3kLaunched 2026-07-30$0.45 in$1.2 out1 public result1 source · 3% coverage
95—gpt-5.2OpenAI · gptMultimodalReasoningTools44.2Overall capability400kLaunched 2025-12-11$1.75 in$14 out1 public result1 source · 3% coverage
96—gpt-5.4-mini-highOpenAI · gpt-miniMultimodalReasoningTools43.9Overall capability400kLaunched 2026-03-17$0.75 in$4.5 out1 public result1 source · 3% coverage
97—grok-4-0709xAI · grokMultimodalReasoningTools43.9Overall capability256kLaunched 2025-07-09$3 in$15 out1 public result1 source · 3% coverage
98—mimo-v2-flash (non-thinking)Xiaomi · mimoReasoningToolsOpen weights43.8Overall capability262.1kLaunched 2025-12-16$0.1 in$0.3 out1 public result1 source · 3% coverage
99—o3-2025-04-16OpenAI · oMultimodalReasoningTools43.3Overall capability200kLaunched 2025-04-16$1.8 in$7.2 out1 public result1 source · 3% coverage
100—nvidia-nemotron-3.5-super-vl-120b-a12b-nvfp4NVIDIA · nemotronMultimodalReasoningTools42.9Overall capability262.1kLaunched 2026-10-15$0.15 in$0.5 out1 public result1 source · 3% coverage
——ClaudeAnthropicText646.7Overall capability—Launch date pending— in— out0 public results0 sources · 0% coverage
——QwenAlibabaText564.7Overall capability—Launch date pending— in— out0 public results0 sources · 0% coverage
——GeminiGoogleText522.8Overall capability—Launch date pending— in— out0 public results0 sources · 0% coverage
——GPT / ChatGPTOpenAIText520.0Overall capability—Launch date pending— in— out0 public results0 sources · 0% coverage
——GLMZhipu AIText499.4Overall capability—Launch date pending— in— out0 public results0 sources · 0% coverage
——KimiMoonshot AIText336.6Overall capability—Launch date pending— in— out0 public results0 sources · 0% coverage
——LlamaMetaText167.2Overall capability—Launch date pending— in— out0 public results0 sources · 0% coverage
——DeepSeekDeepSeekText149.9Overall capability—Launch date pending— in— out0 public results0 sources · 0% coverage
——MistralMistral AIText133.1Overall capability—Launch date pending— in— out0 public results0 sources · 0% coverage
——GrokxAIText94.7Overall capability—Launch date pending— in— out0 public results0 sources · 0% coverage
——Gemini 3.1 Pro PreviewGoogle · gemini-proMultimodalReasoningTools71.4Overall capability1MLaunched 2026-02-18$2 in$12 out0 public results0 sources · 0% coverage
——Gemini 3 ProGoogle · gemini-proMultimodalReasoningTools71.1Overall capability1MLaunched 2025-10-22$1.6 in$9.6 out1 public result1 source · 3% coverage
——qwen3.5-max-previewAlibaba Qwen · qwenToolsStructured67.4Overall capability256kLaunched 2025-09-23$1.2 in$6 out1 public result1 source · 3% coverage
——mimo-v2.5-proXiaomi · mimoMultimodalReasoningTools65.3Overall capability1MLaunched 2026-04-22$1 in$3 out1 public result1 source · 3% coverage
——glm-5.1Zhipu AI · glmReasoningToolsStructured64.3Overall capability202.8kLaunched 2026-04-07$1.05 in$3.5 out1 public result1 source · 3% coverage
——gemini-2.5-proGoogle · gemini-proMultimodalReasoningTools62.5Overall capability1MLaunched 2025-03-20$1.25 in$10 out1 public result1 source · 3% coverage
——kimi-k2.6Moonshot AIMultimodalReasoningTools61.5Overall capability256kLaunched 1970-01-01$0.95 in$4 out1 public result1 source · 3% coverage
——glm-5Zhipu AI · glmReasoningToolsStructured57.7Overall capability202.8kLaunched 2026-02-12$0.6 in$2.08 out1 public result1 source · 3% coverage
——kimi-k2.5-thinkingMoonshot AI · kimi-k2MultimodalReasoningTools57.4Overall capability262.1kLaunched 2026-01-27$0.45 in$2.25 out1 public result1 source · 3% coverage
——Step 5 PreviewstepfunMultimodalReasoningTools55.9Overall capability1MLaunched 2026-09-16$1 in$2.7 out0 public results0 sources · 0% coverage
——qwen3-max-previewAlibaba Qwen · qwenToolsStructured54.9Overall capability256kLaunched 2025-09-23$1.2 in$6 out1 public result1 source · 3% coverage
——gpt-5.2-chat-latest-20260210OpenAI · gptMultimodalReasoningTools54.8Overall capability400kLaunched 2026-01-01$1.75 in$14 out0 public results0 sources · 0% coverage
——hy3Tencent · HyReasoningToolsStructured54.6Overall capability262.1kLaunched 2026-07-06$0.13 in$0.53 out1 public result1 source · 3% coverage
——mimo-v2-proXiaomi · mimoReasoningTools53.8Overall capability1MLaunched 2026-03-18$0 in$0 out1 public result1 source · 3% coverage
——chatgpt-4o-latest-20250326OpenAI · gptMultimodalTools50.7Overall capability128kLaunched 2024-08-14$4.5 in$14 out1 public result1 source · 3% coverage
——mimo-v2.5Xiaomi · mimoMultimodalReasoningTools50.5Overall capability262.1kLaunched 2026-04-22$0.14 in$0.28 out1 public result1 source · 3% coverage
——deepseek-v3.2-exp-thinkingDeepSeek · deepseekTools49.3Overall capability131.1kLaunched 2025-01-01$0.29 in$0.43 out0 public results0 sources · 0% coverage
——deepseek-v3.2DeepSeek · deepseekTools49.1Overall capability131.1kLaunched 2025-01-01$0.29 in$0.43 out1 public result1 source · 3% coverage
——mistral-medium-2508Mistral AI · mistral-mediumMultimodalTools49.1Overall capability262.1kLaunched 2025-08-12$0.4 in$2 out1 public result1 source · 3% coverage
——deepseek-v3.1DeepSeek · deepseekReasoningToolsOpen weights47.2Overall capability131.1kLaunched 2025-08-21$0.6 in$1.7 out1 public result1 source · 3% coverage
——qwen3.5-122b-a10bAlibaba Qwen · qwenMultimodalReasoningTools46.3Overall capability262.1kLaunched 2026-02-23$0.29 in$2.4 out1 public result1 source · 3% coverage
——gemini-2.5-flashGoogle · gemini-flashMultimodalReasoningTools46.1Overall capability1MLaunched 2025-03-20$0.3 in$2.5 out1 public result1 source · 3% coverage
——kimi-k2-thinking-turboMoonshot AIReasoningTools45.2Overall capability262kLaunched 2025-11-06$1.15 in$8 out1 public result1 source · 3% coverage
——qwen3.5-27bAlibaba Qwen · qwenMultimodalReasoningTools42.9Overall capability262.1kLaunched 2026-02-23$0.26 in$2.6 out1 public result1 source · 3% coverage
——grok-4-1-fast-reasoningxAI · grokMultimodalTools42.6Overall capability2MLaunched 2025-11-19$0.2 in$0.5 out1 public result1 source · 3% coverage
——gemini-2.5-flash-preview-09-2025Google · geminiMultimodalReasoningTools41.9Overall capability1MLaunched 2025-09-25$0.3 in$2.5 out1 public result1 source · 3% coverage
——gpt-5-highOpenAI · gpt-codexMultimodalReasoningTools41.8Overall capability128kLaunched 2025-08-07$1.1 in$9 out1 public result1 source · 3% coverage
——hunyuan-vision-1.5-thinkingTencentText41.6Overall capability—Launch date pending— in— out1 public result1 source · 3% coverage
——minimax-m2.7MiniMax · minimaxTools41.3Overall capability192kLaunched 2026-03-18$0.3 in$1.2 out1 public result1 source · 3% coverage
——step-3.5-flashstepfun · stepReasoningToolsStructured40.4Overall capability262kLaunched 2026-02-11$0.1 in$0.3 out1 public result1 source · 3% coverage
——hunyuan-hy3-previewTencentText40.0Overall capability—Launch date pending— in— out1 public result1 source · 3% coverage
——qwen3-vl-235b-a22b-thinkingAlibaba Qwen · qwenMultimodalReasoningOpen weights39.7Overall capability131.1kLaunched 2025-09-23$0.5 in$6 out1 public result1 source · 3% coverage
——grok-4.7-xhighxAI · grokMultimodalReasoningTools39.6Overall capability524.3kLaunched 2026-09-21$2 in$6 out1 public result1 source · 3% coverage
——hunyuan-t1-20250711Tencent · hunyuanReasoningTools39.6Overall capability131.1kLaunched 2026-03-08$0 in$0 out1 public result1 source · 3% coverage
——grok-4-fast-reasoningxAI · grokMultimodalReasoningTools39.2Overall capability2MLaunched 2025-09-16$0.2 in$0.5 out1 public result1 source · 3% coverage
——gpt-6-sol-maxOpenAI · gpt-solMultimodalReasoningTools38.6Overall capability1.1MLaunched 2026-09-22$2 in$10 out1 public result1 source · 3% coverage
——qwen3.5-flashAlibaba Qwen · qwenMultimodalReasoningTools38.2Overall capability1MLaunched 2026-02-23$0.09 in$0.37 out1 public result1 source · 3% coverage
——grok-4.3xAI · grokMultimodalReasoningTools38.1Overall capability1MLaunched 2026-04-30$1.25 in$2.5 out1 public result1 source · 3% coverage
——claude-haiku-4-5-20251001Anthropic · claude-haikuMultimodalReasoningTools38.0Overall capability200kLaunched 2025-10-15$1 in$5 out1 public result1 source · 3% coverage
——amazon-nova-experimental-chat-26-01-10AmazonText37.6Overall capability—Launch date pending— in— out1 public result1 source · 3% coverage
——qwen3.5-35b-a3bAlibaba Qwen · qwenMultimodalReasoningTools37.3Overall capability262.1kLaunched 2026-02-01$0.14 in$1 out1 public result1 source · 3% coverage
——amazon-nova-experimental-chat-10-20AmazonText36.9Overall capability—Launch date pending— in— out1 public result1 source · 3% coverage
——qwen3-235b-a22b-no-thinkingAlibaba Qwen · qwenToolsStructured36.7Overall capability256kLaunched 2025-09-23$1.2 in$6 out1 public result1 source · 3% coverage
——minimax-m2.1-previewMiniMax · minimaxReasoningToolsStructured36.1Overall capability200kLaunched 2025-12-23$0.33 in$1.32 out1 public result1 source · 3% coverage
——gpt-6-luna-maxOpenAI · gpt-lunaMultimodalReasoningTools36.0Overall capability1.1MLaunched 2026-09-22$0.1 in$0.5 out1 public result1 source · 3% coverage
——muse-glimmerMeta · museMultimodalReasoningTools34.9Overall capability131.1kLaunched 2026-08-10$0.2 in$0.8 out1 public result1 source · 3% coverage
——gpt-5.3-chat-latestOpenAI · gptMultimodalReasoningTools34.9Overall capability400kLaunched 2026-03-01$1.75 in$14 out0 public results0 sources · 0% coverage
——solar-pro4OpenAI · solar-proReasoningToolsStructured34.1Overall capability524.3kLaunched 2026-08-06$0.03 in$0.12 out1 public result1 source · 3% coverage
——qwen3-30b-a3b-instruct-2507Alibaba Qwen · qwenToolsStructuredOpen weights32.9Overall capability256kLaunched 2025-02-20$0.2 in$0.5 out1 public result1 source · 3% coverage
——glm-4.5-airZhipu AI · glm-airReasoningToolsOpen weights32.8Overall capability131.1kLaunched 2025-07-28$0.2 in$1.1 out1 public result1 source · 3% coverage
——gpt-4.1-2025-04-14OpenAI · gptMultimodalToolsStructured32.5Overall capability1MLaunched 2025-04-14$1.8 in$7.2 out1 public result1 source · 3% coverage
——kimi-k2-0905-previewMoonshot AI · kimi-k2ToolsStructuredOpen weights31.4Overall capability262.1kLaunched 2025-09-25$0.4 in$1.8 out1 public result1 source · 3% coverage
——gemini-2.5-flash-lite-preview-09-2025-no-thinkingGoogle · gemini-flashMultimodalReasoningTools31.1Overall capability1MLaunched 2025-03-20$0.3 in$2.5 out1 public result1 source · 3% coverage
——nvidia-nemotron-3-super-120b-a12bNVIDIA · nemotronReasoningToolsStructured30.4Overall capability1MLaunched 2026-03-11$0.25 in$2.5 out1 public result1 source · 3% coverage
——hunyuan-turbos-20250416Tencent · hunyuanTools30.2Overall capability131.1kLaunched 2026-03-08$0 in$0 out1 public result1 source · 3% coverage
——claude-opus-4-20250514-thinking-16kAnthropic · claude-opusMultimodalReasoningTools30.2Overall capability192.5kLaunched 2025-05-21$13 in$64 out1 public result1 source · 3% coverage
——glm-4.6vZhipu AI · glmMultimodalReasoningTools29.9Overall capability128kLaunched 2025-12-08$0.3 in$0.9 out1 public result1 source · 3% coverage
——deepseek-v3-0324DeepSeek · deepseekToolsStructuredOpen weights29.2Overall capability163.8kLaunched 2025-03-24$0.24 in$0.9 out1 public result1 source · 3% coverage
——gpt-5-mini-highOpenAI · gpt-miniMultimodalReasoningTools28.7Overall capability400kLaunched 2025-08-07$0.25 in$2 out1 public result1 source · 3% coverage
——deepseek-r1DeepSeek · deepseek-thinkingReasoningToolsStructured28.4Overall capability80kLaunched 2025-01-20$0.5 in$4.88 out1 public result1 source · 3% coverage