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 now165of 230 tracked models
Public evidence532verified benchmark results
Evaluation map96reviewed upstream sources
Builders / multimodal20 / 136providers · rich-input models
Leaders right now

Research & reasoning

Direct public data · prices never affect capability rank
01
MetaMuse Wonder 1.0
Research & reasoning90.6
1M context$20 / 1M out
02
Alibaba QwenQwen3.8 Flash
Research & reasoning87.4
1M context$0.47 / 1M out
03
DeepSeekdeepseek-v4.1-flash-max
Research & reasoning86.7
1M context$0.6 / 1M out
51 matching models · select up to four to compare
Research & reasoning. A score of 50 is the current reference-set average. Price and speed are shown for comparison but never affect rank.
Full ranking

Research & reasoning

Open a model for verified evidence, specifications and related releases
RankModelCapabilityContextAPI pricingEvidenceCompare
02—Muse Wonder 1.0Meta · museMultimodalReasoningTools90.6Research & reasoning1MLaunched 2026-10-12$4 in$20 out4 public results1 source · 90% coverage
10—Qwen3.8 FlashAlibaba Qwen · qwenMultimodalReasoningTools87.4Research & reasoning1MLaunched 2026-08-26$0.16 in$0.47 out4 public results1 source · 90% coverage
13—deepseek-v4.1-flash-maxDeepSeek · deepseek-flashMultimodalReasoningTools86.7Research & reasoning1MLaunched 2026-09-10$0.15 in$0.6 out8 public results3 sources · 100% coverage
62—Deepseek V4 Flash VisionDeepSeek · deepseek-flashMultimodalReasoningTools85.4Research & reasoning1MLaunched 2026-08-21$0.22 in$0.65 out4 public results1 source · 90% coverage
06—Mistral Large 4 0Mistral AIMultimodalReasoningTools85.2Research & reasoning1MLaunched 2026-10-06$0.7 in$2.1 out4 public results1 source · 90% coverage
05—GPT-6 AstraOpenAI · gpt-astraMultimodalReasoningTools84.7Research & reasoning1.1MLaunched 2026-09-04$10 in$50 out9 public results3 sources · 100% coverage
83—Mistral Large 4Mistral AI · mistral-largeMultimodalReasoningTools83.9Research & reasoning1MLaunched 2026-10-06$0.7 in$2.1 out5 public results2 sources · 95% coverage
07—GPT-6.1 SolOpenAI · gpt-solMultimodalReasoningTools83.8Research & reasoning1.1MLaunched 2026-09-29$2 in$10 out9 public results3 sources · 100% coverage
——Step 5 PreviewstepfunMultimodalReasoningTools83.8Research & reasoning1MLaunched 2026-09-16$1 in$2.7 out0 public results0 sources · 0% coverage
17—Step 5 PreviewIndependentMultimodalReasoningTools83.8Research & reasoning1MLaunched 2026-09-16$1 in$2.7 out8 public results3 sources · 100% coverage
09—Gemini 4 ArgonGoogle · geminiMultimodalReasoningTools83.8Research & reasoning1MLaunched 2026-10-13$2 in$10 out9 public results3 sources · 100% coverage
03—Claude Opus 5.5Anthropic · claude-opusMultimodalReasoningTools83.7Research & reasoning1MLaunched 2026-09-22$4 in$20 out9 public results3 sources · 100% coverage
12—Minimax M3.1 FlashMiniMax · minimaxMultimodalReasoningTools82.9Research & reasoning1MLaunched 2026-10-19$0.15 in$0.6 out8 public results2 sources · 100% coverage
04—Claude Fable 5.1Anthropic · claude-fableMultimodalReasoningTools82.5Research & reasoning1MLaunched 2026-09-01$10 in$50 out9 public results3 sources · 100% coverage
08—Claude Sonnet 5.5Anthropic · claude-sonnetMultimodalReasoningTools82.3Research & reasoning1MLaunched 2026-09-28$2 in$10 out9 public results3 sources · 100% coverage
22—GPT-6 LunaOpenAI · gpt-lunaMultimodalReasoningTools81.8Research & reasoning1.1MLaunched 2026-09-22$0.1 in$0.5 out5 public results2 sources · 95% coverage
11—GPT-6.1 TerraOpenAI · gpt-terraMultimodalReasoningTools81.0Research & reasoning1.1MLaunched 2026-10-26$1 in$5 out8 public results2 sources · 100% coverage
15—Kimi K3.1 ProMoonshot AI · kimi-k3MultimodalReasoningTools80.4Research & reasoning1MLaunched 2026-10-23$2 in$10 out8 public results2 sources · 100% coverage
28—Beam 1.0Independent · beamReasoningToolsStructured80.2Research & reasoning1MLaunched 2026-10-05$0 in$0 out4 public results1 source · 90% coverage
21—Qwen3.8-27BAlibaba Qwen · qwenMultimodalReasoningTools80.0Research & reasoning32.8kLaunched 2026-08-14$0.32 in$3.2 out5 public results2 sources · 95% coverage
20—MiMo-V2.6-ProXiaomi · mimoMultimodalReasoningTools79.6Research & reasoning1MLaunched 2026-09-22$0.51 in$1.02 out8 public results3 sources · 100% coverage
55—InklingThinking Machines · lingMultimodalReasoningTools78.3Research & reasoning1MLaunched 2026-07-15$1 in$4.05 out5 public results2 sources · 95% coverage
27—GPT-5.6 TerraOpenAI · gpt-terraMultimodalReasoningTools78.1Research & reasoning1MLaunched 2026-07-09$1.5 in$9 out9 public results3 sources · 100% coverage
19—GLM-5.3-FlashZhipu AI · glm-flashMultimodalReasoningTools77.6Research & reasoning1MLaunched 2026-08-26$0.17 in$0.55 out5 public results2 sources · 95% coverage
16—Gemini 3.8 FlashGoogle · gemini-flashMultimodalReasoningTools77.3Research & reasoning1MLaunched 2026-09-02$0.75 in$3.75 out9 public results3 sources · 100% coverage
25—Muse Spark 1.3Meta · museMultimodalReasoningTools77.2Research & reasoning1MLaunched 2026-09-02$1.25 in$4.25 out9 public results3 sources · 100% coverage
23—Grok 4.6xAI · grokMultimodalReasoningTools77.0Research & reasoning500kLaunched 2026-08-12$2 in$6 out9 public results3 sources · 100% coverage
14—Deepseek V4.1 Flash 1017DeepSeek · deepseek-flashMultimodalReasoningTools76.9Research & reasoning1MLaunched 2026-10-17$0.3 in$1.2 out8 public results2 sources · 100% coverage
36—Kimi K3Moonshot AI · kimi-k3MultimodalReasoningTools76.6Research & reasoning1MLaunched 2026-07-16$3 in$15 out9 public results3 sources · 100% coverage
42—Qwen3.8-MaxAlibaba Qwen · qwenMultimodalReasoningTools75.9Research & reasoning1MLaunched 2026-08-03$2.2 in$6.6 out8 public results3 sources · 100% coverage
44—Smaug Nemotron 3.5 Nvfp4NVIDIAText75.1Research & reasoning—Launch date pending— in— out4 public results1 source · 90% coverage
——Nemotron Ultra 3NVIDIA · nemotronReasoningToolsStructured74.7Research & reasoning202.8kLaunched 2026-06-04$0.6 in$2.4 out4 public results1 source · 90% coverage
46—Nemotron Super Vl 3.5NVIDIA · nemotronText74.6Research & reasoning—Launched 2026-03-11— in— out4 public results1 source · 90% coverage
37—Muse Spark OpenMeta · museMultimodalReasoningTools73.7Research & reasoning1MLaunched 2026-10-15$1.25 in$4.25 out4 public results1 source · 90% coverage
18—Claude Haiku 5.5Anthropic · claude-haikuMultimodalReasoningTools72.9Research & reasoning1MLaunched 2026-10-07$0.1 in$0.5 out8 public results3 sources · 100% coverage
26—Grok 4.7xAI · grokMultimodalReasoningTools72.1Research & reasoning500kLaunched 2026-09-21$2 in$6 out9 public results3 sources · 100% coverage
60—Nemotron Super Vl 3.5 Nvfp4NVIDIAText71.7Research & reasoning—Launch date pending— in— out4 public results1 source · 90% coverage
30—Claude Opus 5Anthropic · claude-opusMultimodalReasoningTools70.6Research & reasoning1MLaunched 2026-07-24$5 in$25 out9 public results3 sources · 100% coverage
29—Muse Wonder FullMeta · museMultimodalReasoningTools70.4Research & reasoning1MLaunched 2026-10-12$4 in$20 out4 public results1 source · 90% coverage
38—GPT-5.6 SolOpenAI · gpt-solMultimodalReasoningTools70.0Research & reasoning1MLaunched 2026-07-09$2.5 in$15 out9 public results3 sources · 100% coverage
31—Claude Fable 5Anthropic · claude-fableMultimodalReasoningTools69.5Research & reasoning1MLaunched 2026-06-09$10 in$50 out9 public results3 sources · 100% coverage
40—GPT-6 SolOpenAI · gpt-solMultimodalReasoningTools69.4Research & reasoning1.1MLaunched 2026-09-22$2 in$10 out9 public results3 sources · 100% coverage
——Gemma 4 31BGoogle · gemmaMultimodalReasoningTools68.3Research & reasoning262.1kLaunched 2026-04-02$0.14 in$0.42 out5 public results2 sources · 95% coverage
33—Muse WonderMeta · museMultimodalReasoningTools67.8Research & reasoning1MLaunched 2026-10-12$4 in$20 out5 public results2 sources · 95% coverage
50—GPT-5.5OpenAI · gptMultimodalReasoningTools67.6Research & reasoning1.1MLaunched 2026-04-23$5 in$30 out9 public results3 sources · 100% coverage
51—Gemini 3.7 FlashGoogle · gemini-flashMultimodalReasoningTools63.9Research & reasoning1MLaunched 2026-08-13$0.75 in$3.75 out9 public results3 sources · 100% coverage
52—Claude Opus 4.8Anthropic · claude-opusMultimodalReasoningTools63.5Research & reasoning1MLaunched 2026-05-28$5 in$25 out9 public results3 sources · 100% coverage
49—GLM-5.3Zhipu AI · glmReasoningToolsStructured61.5Research & reasoning1MLaunched 2026-08-14$1.4 in$4.4 out9 public results3 sources · 100% coverage
47—Qwen3.8 Max 0902Alibaba Qwen · qwenMultimodalReasoningTools61.3Research & reasoning1MLaunched 2026-09-02$2 in$6 out4 public results1 source · 90% coverage
54—Claude Opus 4.7Anthropic · claude-opusMultimodalReasoningTools61.1Research & reasoning1MLaunched 2026-04-16$5 in$25 out5 public results2 sources · 95% coverage
——Nemotron Lightning 3.5NVIDIA · nemotronReasoningToolsStructured42.9Research & reasoning262.1kLaunched 2026-08-15$0.05 in$0.2 out4 public results1 source · 90% coverage