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.

LiveBench 2.0 LMArena models.dev OpenRouter AIHOT cross-check
Ranked now155of 231 tracked models
Public evidence536verified benchmark results
Evaluation map96reviewed upstream sources
Builders / multimodal20 / 131providers · rich-input models
Leaders right now

Best value

Direct public data · prices never affect capability rank
01
MetaMuse Spark 1.3
Best value93.4
1M context$0.2 / 1M out
02
Alibaba QwenQwen3.8 Flash
Best value91.9
1M context$0.47 / 1M out
03
AnthropicClaude Haiku 5.5
Best value90.4
1M context$0.5 / 1M out
199 matching models · select up to four to compare
Best value. A score of 50 is the current reference-set average. Price and speed are shown for comparison but never affect rank.
Full ranking

Best value

Open a model for verified evidence, specifications and related releases
RankModelCapabilityContextAPI pricingEvidenceCompare
25—Muse Spark 1.3Meta · museMultimodalReasoningTools93.4Best value1MLaunched 2026-09-02$0.1 in$0.2 out9 public results3 sources · 100% coverage
10—Qwen3.8 FlashAlibaba Qwen · qwenMultimodalReasoningTools91.9Best value1MLaunched 2026-08-26$0.16 in$0.47 out4 public results1 source · 90% coverage
18—Claude Haiku 5.5Anthropic · claude-haikuMultimodalReasoningTools90.4Best value1MLaunched 2026-10-07$0.1 in$0.5 out8 public results3 sources · 100% coverage
13—deepseek-v4.1-flash-maxDeepSeek · deepseek-flashMultimodalReasoningTools89.6Best value1MLaunched 2026-09-10$0.15 in$0.6 out8 public results3 sources · 100% coverage
12—Minimax M3.1 FlashMiniMax · minimaxMultimodalReasoningTools89.4Best value1MLaunched 2026-10-19$0.15 in$0.6 out8 public results2 sources · 100% coverage
22—GPT-6 LunaOpenAI · gpt-lunaMultimodalReasoningTools89.3Best value1.1MLaunched 2026-09-22$0.1 in$0.5 out5 public results2 sources · 95% coverage
19—GLM-5.3-FlashZhipu AI · glm-flashMultimodalReasoningTools88.3Best value1MLaunched 2026-08-26$0.16 in$0.52 out5 public results2 sources · 95% coverage
43—Muse SparkMeta · museMultimodalReasoningTools88.1Best value1MLaunched 2026-09-02$0.1 in$0.2 out1 public result1 source · 5% coverage
20—MiMo-V2.6-ProXiaomi · mimoMultimodalReasoningTools85.9Best value1MLaunched 2026-09-22$0.44 in$0.87 out8 public results3 sources · 100% coverage
14—Deepseek V4.1 Flash 1017DeepSeek · deepseek-flashMultimodalReasoningTools84.9Best value1MLaunched 2026-10-17$0.17 in$1.2 out8 public results2 sources · 100% coverage
62—MiMo-V2.6-FlashXiaomi · mimoMultimodalReasoningTools81.2Best value1MLaunched 2026-09-22$0.14 in$0.28 out1 public result1 source · 5% coverage
73—NVIDIA-Nemotron-3-Ultra-550B-A55B (NVFP4)NVIDIA · nemotronReasoningToolsStructured80.5Best value131.1kLaunched 2026-06-04$0.1 in$0.1 out1 public result1 source · 5% coverage
06—Mistral Large 4 0Mistral AIMultimodalReasoningTools80.4Best value1MLaunched 2026-10-06$0.7 in$2.1 out4 public results1 source · 90% coverage
53—MiMo-V2.5-ProXiaomi · mimoReasoningToolsStructured75.1Best value1MLaunched 2026-04-22$0.46 in$0.92 out1 public result1 source · 5% coverage
——DeepSeek-V4.1-Flash-20260910DeepSeek · deepseek-flashMultimodalReasoningTools73.6Best value1MLaunched 2026-09-10$0.3 in$1.2 out0 public results0 sources · 0% coverage
17—Step 5 PreviewIndependentMultimodalReasoningTools73.6Best value1MLaunched 2026-09-16$1 in$2.7 out8 public results3 sources · 100% coverage
——Step 5 PreviewstepfunMultimodalReasoningTools73.1Best value1MLaunched 2026-09-16$1.06 in$2.86 out0 public results0 sources · 0% coverage
95—MiMo-V2.5Xiaomi · mimoMultimodalReasoningTools72.1Best value1MLaunched 2026-04-22$0.15 in$0.3 out1 public result1 source · 5% coverage
89—Gemma 4 26B A4BGoogle · gemmaReasoningToolsStructured71.6Best value262.1kLaunched 2026-04-02$0.13 in$0.4 out1 public result1 source · 5% coverage
61—Deepseek V4 Flash VisionDeepSeek · deepseek-flashMultimodalReasoningTools71.3Best value1MLaunched 2026-08-21$0.22 in$0.65 out4 public results1 source · 90% coverage
——deepseek-v3.2-exp-thinkingDeepSeek · deepseekTools70.3Best value131.1kLaunched 2025-01-01$0.29 in$0.43 out0 public results0 sources · 0% coverage
21—Qwen3.8-27BAlibaba Qwen · qwenMultimodalReasoningTools69.9Best value32.8kLaunched 2026-08-14$0.32 in$3.2 out5 public results2 sources · 95% coverage
16—Gemini 3.8 FlashGoogle · gemini-flashMultimodalReasoningTools68.9Best value1MLaunched 2026-09-02$0.75 in$3.75 out9 public results3 sources · 100% coverage
58—Qwen3.7-PlusAlibaba Qwen · qwenMultimodalReasoningTools68.7Best value1MLaunched 2026-06-02$0.32 in$1.28 out1 public result1 source · 5% coverage
——DeepSeek-V3.2DeepSeek · deepseekTools68.0Best value131.1kLaunched 2025-01-01$0.29 in$0.43 out1 public result1 source · 5% coverage
——Gemma 4 31BGoogle · gemmaMultimodalReasoningTools67.9Best value262.1kLaunched 2026-04-02$0.1 in$0.34 out5 public results2 sources · 95% coverage
——amazon-nova-experimental-chat (11-10)Amazon · nova-microTools67.6Best value128kLaunched 2024-12-05$0.037 in$0.15 out0 public results0 sources · 0% coverage
46—GLM-5.2Zhipu AI · glmReasoningToolsStructured67.3Best value200kLaunched 2026-06-13$0.8 in$2.4 out1 public result1 source · 5% coverage
——DeepSeek-V4-Flash PreviewDeepSeek · deepseek-flashReasoningToolsStructured67.1Best value1MLaunched 2026-04-24$0.5 in$0.5 out0 public results0 sources · 0% coverage
65—deepseek-v4-proDeepSeek · deepseek-thinkingReasoningToolsStructured66.9Best value1MLaunched 2026-08-13$0.66 in$1.98 out1 public result1 source · 5% coverage
11—GPT-6.1 TerraOpenAI · gpt-terraMultimodalReasoningTools65.1Best value1.1MLaunched 2026-10-26$1 in$5 out8 public results2 sources · 100% coverage
——MiMo-V2-Flash (Non-Thinking)Xiaomi · mimoReasoningToolsOpen weights64.1Best value256kLaunched 2025-12-16$0.1 in$0.3 out1 public result1 source · 5% coverage
——Gemini 3.6 FlashGoogle · gemini-flashMultimodalReasoningTools63.9Best value1MLaunched 2026-07-21$0.75 in$3.75 out1 public result1 source · 5% coverage
48—ERNIE 5.1Baidu · ernieReasoning63.5Best value119kLaunched 2026-05-10$0.75 in$3 out1 public result1 source · 5% coverage
91—MiniMax-M3MiniMax · minimaxMultimodalReasoningTools62.2Best value1MLaunched 2026-06-01$0.31 in$1.25 out5 public results2 sources · 95% coverage
42—Qwen3.7-Max-PreviewAlibaba Qwen · qwenReasoningToolsStructured61.7Best value1MLaunched 2026-05-21$1.25 in$3.75 out1 public result1 source · 5% coverage
——Step-3.5-Flashstepfun · stepReasoningToolsStructured61.6Best value256kLaunched 2026-01-29$0.1 in$0.3 out1 public result1 source · 5% coverage
23—Grok 4.6xAI · grokMultimodalReasoningTools61.2Best value524.3kLaunched 2026-08-12$2 in$6 out9 public results3 sources · 100% coverage
——Qwen3-VL-235B-A22B-InstructAlibaba Qwen · qwenMultimodalToolsStructured60.9Best value262.1kLaunched 2025-09-23$0.2 in$0.88 out1 public result1 source · 5% coverage
64—Grok 4.20 Multi-Agent Beta (0309)xAI · grokMultimodalReasoningTools60.7Best value2MLaunched 2026-03-11$1.25 in$2.5 out1 public result1 source · 5% coverage
33—Muse Spark 1.2Meta · museMultimodalReasoningTools60.5Best value1MLaunched 2026-08-05$1.32 in$4.5 out8 public results3 sources · 100% coverage
26—Grok 4.7xAI · grokMultimodalReasoningTools60.4Best value524.3kLaunched 2026-09-21$2 in$6 out9 public results3 sources · 100% coverage
07—GPT-6.1 SolOpenAI · gpt-solMultimodalReasoningTools60.2Best value1.1MLaunched 2026-09-29$2 in$10 out9 public results3 sources · 100% coverage
——qwen3-235b-a22b-thinking-2507Alibaba Qwen · qwenReasoningToolsOpen weights60.2Best value262.1kLaunched 2025-07-01$0.11 in$0.6 out1 public result1 source · 5% coverage
37—Muse Spark OpenMeta · museMultimodalReasoningTools60.1Best value1MLaunched 2026-10-15$1.25 in$4.25 out4 public results1 source · 90% coverage
——Qwen3-235B-A22B-Instruct (2507)Alibaba Qwen · qwenToolsStructuredOpen weights60.1Best value262.1kLaunched 2025-08-13$0.22 in$0.88 out1 public result1 source · 5% coverage
——qwen3-235b-a22b-instruct-2507Alibaba Qwen · qwenReasoningToolsStructured60.0Best value262.1kLaunched 2025-07-21$0.22 in$0.88 out1 public result1 source · 5% coverage
——Grok 4.1 FastxAI · grokMultimodalTools59.9Best value2MLaunched 2025-11-17$0.2 in$0.5 out1 public result1 source · 5% coverage
08—Claude Sonnet 5.5Anthropic · claude-sonnetMultimodalReasoningTools59.9Best value1MLaunched 2026-09-28$2 in$10 out9 public results3 sources · 100% coverage
74—nvidia-nemotron-3-ultra-550b-a55b-nvfp4NVIDIA · nemotronReasoningToolsStructured59.9Best value1MLaunched 2026-06-04$0.6 in$2.4 out1 public result1 source · 5% coverage
09—Gemini 4 ArgonGoogle · geminiMultimodalReasoningTools59.6Best value1MLaunched 2026-10-13$2 in$10 out9 public results3 sources · 100% coverage
——nvidia-nemotron-3.5-super-vl-120b-a12b-nvfp4NVIDIA · nemotronMultimodalReasoningTools59.5Best value1MLaunched 2026-10-15$0.2 in$0.5 out1 public result1 source · 5% coverage
81—GLM-4.6Zhipu AI · glmReasoningToolsStructured59.5Best value202.8kLaunched 2025-09-30$0.55 in$2.2 out1 public result1 source · 5% coverage
51—Gemini 3.7 FlashGoogle · gemini-flashMultimodalReasoningTools59.3Best value1MLaunched 2026-08-13$0.75 in$3.75 out9 public results3 sources · 100% coverage
——NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)NVIDIA · nemotronMultimodalReasoningTools59.1Best value1MLaunched 2026-10-15$0.2 in$0.5 out1 public result1 source · 5% coverage
94—Mistral Large 3Mistral AI · mistral-largeMultimodalToolsOpen weights58.4Best value262.1kLaunched 2025-12-02$0.5 in$1.5 out1 public result1 source · 5% coverage
——Qwen3.5-FlashAlibaba Qwen · qwenMultimodalReasoningTools58.4Best value1MLaunched 2026-02-23$0.1 in$0.4 out1 public result1 source · 5% coverage
——solar-pro4OpenAI · solar-proReasoningToolsStructured58.3Best value524.3kLaunched 2026-08-06$0.0413 in$0.17 out1 public result1 source · 5% coverage
——DeepSeek-V3.1-TerminusDeepSeek · deepseekReasoningToolsStructured57.8Best value128kLaunched 2025-06-01$0.27 in$1 out1 public result1 source · 5% coverage
——Qwen3-30B-A3B-Instruct (2507)Alibaba Qwen · qwenToolsStructuredOpen weights57.8Best value131.1kLaunched 2025-07-28$0.09 in$0.3 out1 public result1 source · 5% coverage
40—Muse Spark 1.1Meta · museMultimodalReasoningTools57.7Best value1MLaunched 2026-04-08$1.32 in$4.5 out1 public result1 source · 5% coverage
50—GLM-5.3Zhipu AI · glmReasoningToolsStructured57.4Best value1MLaunched 2026-08-14$1.2 in$4.18 out9 public results3 sources · 100% coverage
——GLM-4.7Zhipu AI · glmReasoningToolsStructured57.3Best value204.8kLaunched 2025-12-22$0.42 in$2.2 out1 public result1 source · 5% coverage
——qwen3-30b-a3b-instruct-2507Alibaba Qwen · qwenToolsStructured57.2Best value262kLaunched 2025-07-30$0.09 in$0.3 out1 public result1 source · 5% coverage
——Solar Pro 4OpenAI · solar-proReasoningToolsStructured56.5Best value524.3kLaunched 2026-08-06$0.0952 in$0.38 out1 public result1 source · 5% coverage
——Kimi K2.5 (Thinking)Moonshot AI · kimi-k2MultimodalReasoningTools56.3Best value262.1kLaunched 2026-01-27$0.6 in$3 out1 public result1 source · 5% coverage
27—GPT-5.6 TerraOpenAI · gpt-terraMultimodalReasoningTools56.1Best value1MLaunched 2026-07-09$1.5 in$9 out9 public results3 sources · 100% coverage
——GLM-4.5Zhipu AI · glmReasoningToolsStructured55.9Best value131.1kLaunched 2025-07-28$0.6 in$2.2 out1 public result1 source · 5% coverage
——mistral-medium-2508Mistral AI · mistral-mediumMultimodalTools55.9Best value262.1kLaunched 2025-08-12$0.4 in$2 out1 public result1 source · 5% coverage
——GLM-5Zhipu AI · glmReasoningToolsStructured55.6Best value200kLaunched 2026-02-12$1 in$3.2 out1 public result1 source · 5% coverage
78—Gemini 3 Flash (Minimal)Google · gemini-flashMultimodalReasoningTools55.5Best value1MLaunched 2025-12-17$0.5 in$3 out1 public result1 source · 5% coverage
57—Kimi K2.6Moonshot AI · kimi-k2MultimodalReasoningTools55.3Best value262.1kLaunched 2026-04-20$0.98 in$4 out1 public result1 source · 5% coverage
88—Gemini 3.5 Flash-LiteGoogle · gemini-flash-liteMultimodalReasoningTools55.2Best value1MLaunched 2026-07-21$0.3 in$2.5 out1 public result1 source · 5% coverage
44—Qwen3.8-MaxAlibaba Qwen · qwenMultimodalReasoningTools55.1Best value1MLaunched 2026-08-03$2 in$6 out8 public results3 sources · 100% coverage
76—ernie-5.0-0110BaiduMultimodalReasoningTools54.7Best value128kLaunched 2026-01-22$0.84 in$3.37 out1 public result1 source · 5% coverage
02—Muse Wonder 1.0Meta · museMultimodalReasoningTools54.6Best value1MLaunched 2026-10-12$4 in$20 out4 public results1 source · 90% coverage
54—Inkling 2 SmallThinking Machines · lingMultimodalReasoningTools54.6Best value1MLaunched 2026-07-15$1.06 in$4.28 out4 public results1 source · 90% coverage
35—Gemini 3.5 FlashGoogle · gemini-flashMultimodalReasoningTools54.5Best value1MLaunched 2026-05-19$1.5 in$9 out1 public result1 source · 5% coverage
——Hy3 previewTencent · HyReasoningToolsStructured54.4Best value262.1kLaunched 2026-07-06$0.21 in$0.85 out0 public results0 sources · 0% coverage
03—Claude Opus 5.5Anthropic · claude-opusMultimodalReasoningTools54.3Best value1MLaunched 2026-09-22$4 in$20 out9 public results3 sources · 100% coverage
——gemini-2.5-flash-lite-preview-09-2025-no-thinkingGoogle · gemini-flash-liteMultimodalReasoningTools54.3Best value1MLaunched 2026-01$0.09 in$0.36 out1 public result1 source · 5% coverage
——Hy3Tencent · HyReasoningToolsStructured54.2Best value262.1kLaunched 2026-07-06$0.14 in$0.58 out1 public result1 source · 5% coverage
80—ernie-5.0-preview-1203BaiduMultimodalReasoningTools54.2Best value128kLaunched 2026-01-22$0.84 in$3.37 out1 public result1 source · 5% coverage
55—InklingThinking Machines · lingMultimodalReasoningTools54.0Best value1MLaunched 2026-07-15$1.06 in$4.28 out5 public results2 sources · 95% coverage
——Qwen3-Next-80B-A3B-InstructAlibaba Qwen · qwenToolsStructuredOpen weights53.9Best value129kLaunched 2025-09$0.16 in$1.27 out1 public result1 source · 5% coverage
98—Mistral Medium 3.1 (2508)Mistral AI · mistral-mediumMultimodalToolsStructured53.8Best value131.1kLaunched 2025-08-12$0.42 in$2.12 out1 public result1 source · 5% coverage
——GLM-5.1Zhipu AI · glmReasoningToolsStructured53.7Best value200kLaunched 2026-04-07$1.2 in$4.4 out1 public result1 source · 5% coverage
85—Qwen3.6-PlusAlibaba Qwen · qwenMultimodalReasoningTools53.6Best value983.6kLaunched 2026-04-02$0.5 in$3 out1 public result1 source · 5% coverage
——DeepSeek-V4-Pro PreviewDeepSeek · deepseek-thinkingReasoningToolsStructured53.6Best value1MLaunched 2026-04-24$1.8 in$3.6 out0 public results0 sources · 0% coverage
86—MiMo-V2-ProXiaomi · mimoReasoningTools53.3Best value1MLaunched 2026-03-18$1 in$3 out1 public result1 source · 5% coverage
49—Qwen3.8 Max 0902Alibaba Qwen · qwenMultimodalReasoningTools53.3Best value983.6kLaunched 2026-09-02$2 in$6 out4 public results1 source · 90% coverage
——gemini-3.1-flash-lite-previewGoogle · gemini-flash-liteMultimodalReasoningTools53.2Best value1MLaunched 2026-05-07$0.25 in$1.5 out1 public result1 source · 5% coverage
——DeepSeek-V3.1DeepSeek · deepseekTools53.1Best value131.1kLaunched 2025-01-01$0.57 in$1.72 out1 public result1 source · 5% coverage
——ERNIE-5.0-Preview (1203)BaiduMultimodalReasoningTools52.5Best value128kLaunched 2026-01-22$0.84 in$3.37 out0 public results0 sources · 0% coverage
——Qwen3.5-Max-PreviewAlibaba Qwen · qwenTools52.5Best value32kLaunched 2024-04-03$1.6 in$6.4 out1 public result1 source · 5% coverage
——Gemini 3.1 Flash-Lite PreviewGoogle · gemini-flash-liteMultimodalReasoningTools51.8Best value1MLaunched 2026-03-03$0.26 in$1.59 out0 public results0 sources · 0% coverage
——kimi-k2.5-instantMoonshot AI · kimi-thinkingReasoningToolsStructured51.4Best value32.8kLaunched 2024-11-01$0.55 in$2.25 out1 public result1 source · 5% coverage
——gpt-oss-120bOpenAI · gpt-ossReasoningToolsStructured51.3Best value131kLaunched 2025-08-05$0.05 in$0.45 out1 public result1 source · 5% coverage
——MiniMax-M2.7MiniMax · minimaxReasoningToolsStructured51.3Best value204.8kLaunched 2026-03-18$0.31 in$1.25 out1 public result1 source · 5% coverage
——Inkling-SmallThinking Machines · lingMultimodalReasoningTools51.3Best value524.3kLaunched 2026-07-30$0.61 in$1.52 out1 public result1 source · 5% coverage
41—GPT-6 SolOpenAI · gpt-solMultimodalReasoningTools51.1Best value1.1MLaunched 2026-09-22$2 in$10 out9 public results3 sources · 100% coverage
04—Claude Fable 5.1Anthropic · claude-fableMultimodalReasoningTools51.0Best value1MLaunched 2026-09-01$10 in$50 out9 public results3 sources · 100% coverage
——Grok 3 MinixAI · grokReasoningTools50.9Best value131.1kLaunched 2025-04-11$0.3 in$0.5 out1 public result1 source · 5% coverage
84—Qwen3.5-397B-A17BAlibaba Qwen · qwenReasoningToolsStructured50.8Best value262.1kLaunched 2026-02-15$0.6 in$3.6 out1 public result1 source · 5% coverage
05—GPT-6 AstraOpenAI · gpt-astraMultimodalReasoningTools50.7Best value1.1MLaunched 2026-09-04$10 in$50 out9 public results3 sources · 100% coverage
——Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)Google · gemini-flash-liteMultimodalReasoning50.6Best value1MLaunched 2025-06-17$0.15 in$0.6 out0 public results0 sources · 0% coverage
——Gemini 3.1 Pro PreviewGoogle · gemini-proMultimodalReasoningTools50.6Best value1MLaunched 2026-02-19$2 in$12 out0 public results0 sources · 0% coverage
66—grok-4.20-beta-0309-reasoningxAI · grokMultimodalTools50.1Best value2MLaunched 2026-03-09$2 in$6 out1 public result1 source · 5% coverage
——Gemini 3 ProGoogle · gemini-proMultimodalReasoningTools50.0Best value1MLaunched 2025-11-18$2 in$12 out1 public result1 source · 5% coverage
93—ernie-5.0-preview-1022BaiduMultimodalReasoningTools49.9Best value128kLaunched 2026-01-22$0.84 in$3.37 out1 public result1 source · 5% coverage
67—grok-4.20-multi-agent-beta-0309xAI · grokReasoningTools49.8Best value262kLaunched 2026-04-08$2 in$6 out1 public result1 source · 5% coverage
——Qwen3-235B-A22B (Non-Thinking)Alibaba Qwen · qwenReasoningToolsStructured49.5Best value131.1kLaunched 2025-04-28$0.29 in$1.15 out1 public result1 source · 5% coverage
——Nemotron Lightning 3.5NVIDIA · nemotronReasoningToolsStructured49.4Best value262.1kLaunched 2026-08-15$0.05 in$0.2 out4 public results1 source · 90% coverage
83—GLM-5V-TurboZhipu AI · glmMultimodalReasoningTools49.3Best value202.8kLaunched 2026-04-01$1.2 in$4 out1 public result1 source · 5% coverage
79—Mistral Large 4Mistral AI · mistral-largeMultimodalReasoningTools49.2Best value1MLaunched 2026-10-06$1.36 in$4.18 out5 public results2 sources · 95% coverage
——GLM-4.5-AirZhipu AI · glm-airReasoningToolsOpen weights48.4Best value128kLaunched 2025-07-28$0.2 in$1.1 out1 public result1 source · 5% coverage
36—Kimi K3Moonshot AI · kimi-k3MultimodalReasoningTools48.2Best value1MLaunched 2026-07-16$3 in$15 out9 public results3 sources · 100% coverage
24—Claude Opus 4.6Anthropic · claude-opusMultimodalReasoningTools48.2Best value1MLaunched 2026-02-05$5 in$25 out1 public result1 source · 5% coverage
——Qwen2.5-MaxAlibaba Qwen · qwenMultimodalOpen weights48.0Best value65.5kLaunched 2025-01-26$0.7 in$0.7 out1 public result1 source · 5% coverage
69—Grok 4.5xAI · grokMultimodalReasoningTools48.0Best value500kLaunched 2026-07-08$2 in$6 out5 public results2 sources · 95% coverage
——MiniMax-M2.1 PreviewMiniMax · minimaxReasoningToolsOpen weights48.0Best value204.8kLaunched 2025-12-23$0.31 in$1.25 out0 public results0 sources · 0% coverage
——minimax-m2.1-previewMiniMax · minimaxReasoningToolsStructured47.8Best value204.8kLaunched 2025-12-23$0.3 in$1.2 out1 public result1 source · 5% coverage
38—GPT-5.6 SolOpenAI · gpt-solMultimodalReasoningTools47.7Best value1MLaunched 2026-07-09$2.5 in$15 out9 public results3 sources · 100% coverage
——GLM-4.6VZhipu AI · glmMultimodalReasoningTools47.6Best value131.1kLaunched 2025-12-08$0.32 in$0.95 out1 public result1 source · 5% coverage
75—grok-4.20-beta1xAI · grokReasoningTools47.4Best value262kLaunched 2026-04-08$2 in$6 out1 public result1 source · 5% coverage
30—Claude Opus 5Anthropic · claude-opusMultimodalReasoningTools47.1Best value1MLaunched 2026-07-24$5 in$25 out9 public results3 sources · 100% coverage
34—Muse WonderMeta · museMultimodalReasoningTools46.9Best value1MLaunched 2026-10-12$4 in$20 out5 public results2 sources · 95% coverage
——DeepSeek-V3 (0324)DeepSeek · deepseekToolsStructuredOpen weights46.8Best value131.1kLaunched 2024-12-26$0.28 in$1.1 out1 public result1 source · 5% coverage
——gemini-2.5-flashGoogle · gemini-flashMultimodalReasoningTools46.7Best value1MLaunched 2025-06-17$0.3 in$2.5 out1 public result1 source · 5% coverage
32—Claude Opus 4.7Anthropic · claude-opusMultimodalReasoningTools46.5Best value1MLaunched 2026-04-16$5 in$25 out5 public results2 sources · 95% coverage
——Qwen3.5-35B-A3BAlibaba Qwen · qwenReasoningToolsStructured46.4Best value262.1kLaunched 2026-02-23$0.25 in$1.3 out1 public result1 source · 5% coverage
——Kimi K2 Thinking TurboMoonshot AI · kimi-thinkingReasoningToolsStructured46.4Best value262.1kLaunched 2025-11-13$0.6 in$2.5 out1 public result1 source · 5% coverage
——Gemini 2.5 ProGoogle · gemini-proMultimodalReasoningTools45.9Best value1MLaunched 2025-06-17$1.25 in$10 out1 public result1 source · 5% coverage
——DeepSeek V4.1 FlashDeepSeek · deepseek-flashMultimodalReasoningTools45.8Best value1MLaunched 2026-09-10$0.6 in$2.4 out2 public results1 source · 45% coverage
——deepseek-v3-0324DeepSeek · deepseekToolsStructuredOpen weights45.4Best value163.8kLaunched 2026-01$0.28 in$1.14 out1 public result1 source · 5% coverage
——Qwen3.5-27BAlibaba Qwen · qwenReasoningToolsStructured45.4Best value262.1kLaunched 2026-02-23$0.3 in$2.4 out1 public result1 source · 5% coverage
92—GPT-5.6 LunaOpenAI · gpt-lunaMultimodalReasoningTools45.0Best value1MLaunched 2026-07-09$0.7 in$4.2 out5 public results2 sources · 95% coverage
29—Muse Wonder FullMeta · museMultimodalReasoningTools45.0Best value1MLaunched 2026-10-12$4 in$20 out4 public results1 source · 90% coverage
70—Qwen3.6-Max-PreviewAlibaba Qwen · qwenReasoningToolsStructured45.0Best value256kLaunched 2026-04-20$1.31 in$7.88 out1 public result1 source · 5% coverage
82—Qwen3-Max-PreviewAlibaba Qwen · qwenTools44.7Best value262.1kLaunched 2025-09-23$1.2 in$6 out1 public result1 source · 5% coverage
31—Claude Fable 5Anthropic · claude-fableMultimodalReasoningTools44.7Best value1MLaunched 2026-06-09$10 in$50 out9 public results3 sources · 100% coverage
——Muse GlimmerMeta · museMultimodalReasoningTools44.4Best value131.1kLaunched 2026-08-10$0.37 in$1.59 out1 public result1 source · 5% coverage
——Qwen3.5-122B-A10BAlibaba Qwen · qwenReasoningToolsStructured44.1Best value262.1kLaunched 2026-02-23$0.4 in$3.2 out1 public result1 source · 5% coverage
——DeepSeek-V4-FlashDeepSeek · deepseek-flashReasoningToolsStructured44.0Best value1MLaunched 2026-04-24$0.44 in$1.32 out5 public results2 sources · 95% coverage
——Qwen3-Next-80B-A3B-ThinkingAlibaba Qwen · qwenReasoningToolsOpen weights43.9Best value262.1kLaunched 2025-09$0.15 in$1.2 out1 public result1 source · 5% coverage
——Gemini 2.5 Flash Preview (09-2025)Google · geminiMultimodalReasoningTools43.9Best value1MLaunched 2025-09-25$0.3 in$2.5 out0 public results0 sources · 0% coverage
——Nemotron Ultra 3NVIDIA · nemotronReasoningToolsStructured42.8Best value202.8kLaunched 2026-06-04$0.6 in$2.4 out4 public results1 source · 90% coverage
——gemini-2.5-flash-preview-09-2025Google · geminiMultimodalReasoningTools42.5Best value1MLaunched 2025-09-25$0.3 in$2.5 out1 public result1 source · 5% coverage
39—GPT-5.5OpenAI · gptMultimodalReasoningTools42.3Best value1.1MLaunched 2026-04-23$5 in$30 out9 public results3 sources · 100% coverage
56—Claude Sonnet 4.6Anthropic · claude-sonnetMultimodalReasoningTools41.9Best value1MLaunched 2026-02-17$3 in$15 out5 public results2 sources · 95% coverage
——GPT-5.4 nanoOpenAI · gpt-nanoMultimodalReasoningTools41.7Best value400kLaunched 2026-03-17$0.21 in$1.32 out1 public result1 source · 5% coverage
——Grok 4 FastxAI · grokMultimodalTools41.4Best value2MLaunched 2025-12-18$1.25 in$2.5 out1 public result1 source · 5% coverage
77—Claude Sonnet 5Anthropic · claude-sonnetMultimodalReasoningTools41.2Best value1MLaunched 2026-06-30$2 in$10 out5 public results2 sources · 95% coverage
——Grok 4.3xAI · grokReasoningTools40.9Best value200kLaunched 2026-04-30$1.25 in$2.5 out1 public result1 source · 5% coverage
60—GPT-5.4OpenAI · gptMultimodalReasoningTools40.5Best value1.1MLaunched 2026-03-05$2.5 in$15 out1 public result1 source · 5% coverage
——qwen3-max-2025-09-23Alibaba QwenTools40.5Best value258kLaunched 2025-09-24$0.86 in$3.43 out1 public result1 source · 5% coverage
——GPT-5 miniOpenAI · gpt-miniMultimodalReasoningTools40.1Best value400kLaunched 2025-08-07$0.25 in$2 out1 public result1 source · 5% coverage
——Grok 4.20 BetaxAI · grokMultimodalReasoningTools40.0Best value256kLaunched 2025-07-09$3 in$15 out1 public result1 source · 5% coverage
52—Claude Opus 4.8Anthropic · claude-opusMultimodalReasoningTools39.9Best value1MLaunched 2026-05-28$5 in$25 out9 public results3 sources · 100% coverage
——Mistral Medium 3 (2505)Mistral AI · mistral-mediumMultimodalToolsStructured39.0Best value131.1kLaunched 2025-05-07$0.4 in$2 out1 public result1 source · 5% coverage
——DeepSeek-R1DeepSeek · deepseek-thinkingReasoningToolsOpen weights38.6Best value131.1kLaunched 2025-01-20$0.55 in$2.2 out1 public result1 source · 5% coverage
——NVIDIA-Nemotron-3-Super-120B-A12BNVIDIA · nemotronReasoningToolsStructured38.5Best value262.1kLaunched 2026-03-11$0.3 in$2.4 out1 public result1 source · 5% coverage
87—Grok 4.1xAIMultimodalTools38.5Best value200kLaunched 2025-11-18$2 in$10 out1 public result1 source · 5% coverage
——kimi-k2-0905-previewMoonshot AI · kimi-k2ToolsStructuredOpen weights38.4Best value262.1kLaunched 2026-01$0.6 in$2.5 out1 public result1 source · 5% coverage
——Grok 4.20 Beta 1xAI · grokMultimodalReasoningTools37.3Best value256kLaunched 2025-07-09$3 in$15 out1 public result1 source · 5% coverage
——deepseek-r1-0528DeepSeek · deepseek-thinkingReasoningToolsStructured37.2Best value128kLaunched 2025-01-20$2 in$8.75 out1 public result1 source · 5% coverage
63—Claude Opus 4.5 (20251101)Anthropic · claude-opusMultimodalReasoningTools36.1Best value200kLaunched 2025-11-24$5 in$25 out1 public result1 source · 5% coverage
72—claude-opus-4-5-20251101-high-32kAnthropic · claude-opusMultimodalReasoningTools35.9Best value200kLaunched 2025-11-01$5 in$25 out1 public result1 source · 5% coverage
100—Mistral Medium 3.5Mistral AI · mistral-mediumMultimodalReasoningTools34.8Best value262.1kLaunched 2026-04-30$1.59 in$7.94 out1 public result1 source · 5% coverage
——Qwen3-VL-235B-A22B-ThinkingAlibaba Qwen · qwenMultimodalReasoningTools34.4Best value131.1kLaunched 2025-09-23$0.4 in$4 out1 public result1 source · 5% coverage
90—claude-sonnet-4-5-20250929-high-32kAnthropic · claude-sonnetMultimodalReasoningTools34.1Best value200kLaunched 2025-09-29$3 in$15 out1 public result1 source · 5% coverage
——Kimi K2 Preview (0711)Moonshot AI · kimi-thinkingReasoningToolsStructured33.8Best value262.1kLaunched 2025-11-06$0.63 in$2.65 out0 public results0 sources · 0% coverage
——Claude Sonnet 4.5Anthropic · claude-sonnetMultimodalReasoningTools33.4Best value200kLaunched 2025-09-29$3 in$15 out1 public result1 source · 5% coverage
99—GPT-5.1OpenAI · gptMultimodalReasoningTools33.3Best value400kLaunched 2025-11-13$1.25 in$10 out1 public result1 source · 5% coverage
——ChatGPT-4o Latest (20250326)OpenAI · gptMultimodalTools32.9Best value128kLaunched 2024-08-14$4.5 in$14 out0 public results0 sources · 0% coverage
——grok-3-preview-02-24xAI · grokTools31.1Best value131.1kLaunched 2024-06-01$3 in$15 out1 public result1 source · 5% coverage
——Grok 3 Preview (02-24)xAI · grokTools30.9Best value131.1kLaunched 2025-04-11$3 in$15 out0 public results0 sources · 0% coverage
——chatgpt-4o-latest-20250326OpenAI · gptMultimodalTools30.2Best value128kLaunched 2024-08-14$5 in$20 out1 public result1 source · 5% coverage
——Claude Haiku 4.5 (20251001)Anthropic · claude-haikuMultimodalReasoningTools29.4Best value200kLaunched 2025-10-15$1 in$5 out5 public results2 sources · 95% coverage
——o3 (2025-04-16)OpenAI · oMultimodalReasoningTools29.3Best value200kLaunched 2025-04-16$2 in$8 out1 public result1 source · 5% coverage
——o3-2025-04-16OpenAI · oMultimodalReasoningTools29.0Best value200kLaunched 2025-04-16$2 in$8 out1 public result1 source · 5% coverage
——GPT-5.4 miniOpenAI · gpt-miniMultimodalReasoningTools28.9Best value400kLaunched 2026-03-17$1.59 in$9.52 out1 public result1 source · 5% coverage
——qwen3-235b-a22b-no-thinkingAlibaba Qwen · qwenTools27.1Best value262.1kLaunched 2025-09-23$1.2 in$6 out1 public result1 source · 5% coverage
——GPT-5 ChatOpenAI · gptMultimodalReasoningTools25.8Best value400kLaunched 2025-08-07$1.25 in$10 out0 public results0 sources · 0% coverage
——gpt-5-highOpenAI · gptMultimodalReasoningTools25.6Best value128kLaunched 2025-08-07$1.25 in$10 out1 public result1 source · 5% coverage
——GPT-5.2OpenAI · gptMultimodalReasoningTools25.5Best value400kLaunched 2025-12-11$1.75 in$14 out1 public result1 source · 5% coverage
——Grok 4 (0709)xAI · grokMultimodalReasoningTools24.1Best value256kLaunched 2025-07-09$3 in$15 out1 public result1 source · 5% coverage
——grok-4-0709xAI · grokMultimodalToolsStructured23.4Best value256kLaunched 2026-01$2.7 in$13.5 out1 public result1 source · 5% coverage
——GPT-4.1 (2025-04-14)OpenAI · gptMultimodalToolsStructured22.7Best value1MLaunched 2025-04-14$2 in$8 out1 public result1 source · 5% coverage
——GPT-5.5 InstantOpenAIMultimodalReasoningTools22.5Best value400kLaunched 2026-05-05$5 in$30 out1 public result1 source · 5% coverage
——gpt-4.1-2025-04-14OpenAI · gptMultimodalToolsStructured22.3Best value1MLaunched 2025-04-14$2 in$8 out1 public result1 source · 5% coverage
——claude-opus-4-1-20250805-thinking-16kAnthropic · claude-opusMultimodalReasoningTools21.0Best value200kLaunched 2025-08-05$15 in$75 out1 public result1 source · 5% coverage
——GPT-4.5 Preview (2025-02-27)OpenAI · gptToolsStructured19.9Best value8.2kLaunched 2023-11-06$30 in$60 out0 public results0 sources · 0% coverage
——Claude Opus 4.1 (20250805)Anthropic · claude-opusMultimodalReasoningTools19.8Best value200kLaunched 2025-08-05$15 in$75 out1 public result1 source · 5% coverage
——GPT-5.3 ChatOpenAI · gptMultimodalTools18.9Best value400kLaunched 2026-03-03$1.75 in$14 out0 public results0 sources · 0% coverage
——gpt-4.5-preview-2025-02-27OpenAI · gptToolsStructured18.5Best value8kLaunched 2023-11-06$39 in$78 out1 public result1 source · 5% coverage
——GPT-5.2 Chat (20260210)OpenAI · gptMultimodalToolsStructured17.1Best value128kLaunched 2025-12-11$1.6 in$13 out0 public results0 sources · 0% coverage
——claude-opus-4-20250514-thinking-16kAnthropic · claude-opusMultimodalToolsStructured7.2Best value200kLaunched 2026-01$13.5 in$67.5 out1 public result1 source · 5% coverage
——Claude Opus 4 (20250514)Anthropic · claude-opusMultimodalReasoningTools6.1Best value192.5kLaunched 2025-05-22$13 in$64 out1 public result1 source · 5% coverage