Reasoning and knowledge rankings.
A clean reasoning surface that starts with available Arena signals and keeps LiveBench, HELM Capabilities, MMLU-Pro, GPQA, and AIME-style math benchmarks visible as planned source integrations.
Ranked models
142
Text, docs, or vision signal
Reasoning variants
50
Models tagged from public names
Top proxy
Claude Fable 5
100 reasoning proxy
LiveBench
Planned
Fresh reasoning feed
Reasoning formula
A proxy until dedicated reasoning feeds are wired.
The current index blends Text, Docs, and Vision Arena scores. It is useful for broad comparison, but dedicated LiveBench, GPQA, AIME, MMLU-Pro, and HELM signals should be treated as the next data layer.
Reasoning and knowledge proxy
Higher proxy index is better. Dedicated reasoning benchmarks are source-ready but not silently mixed in yet.
Top 30 of 142
| Rank | Model | Index | Text | Docs | Vision | Mode | Sources |
|---|---|---|---|---|---|---|---|
| #1 | 100reasoning proxy | 1,507Text Arena rank #1 | 1,507Docs Arena rank #1 | 1,313Vision Arena rank #1 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #2 | 95reasoning proxy | 1,505Text Arena rank #2 | Not listedDocs Arena | 1,299Vision Arena rank #5 | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #3 | 93reasoning proxy | 1,502Text Arena rank #3 | Not listedDocs Arena | 1,301Vision Arena rank #2 | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #4 | 90reasoning proxy | Not listedText Arena | 1,496Docs Arena rank #3 | Not listedVision Arena | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #5 | 89reasoning proxy | 1,499Text Arena rank #4 | Not listedDocs Arena | 1,292Vision Arena rank #8 | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #6 | 88reasoning proxy | 1,498Text Arena rank #5 | 1,495Docs Arena rank #4 | 1,293Vision Arena rank #7 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #7 | 88reasoning proxy | 1,494Text Arena rank #6 | 1,497Docs Arena rank #2 | 1,299Vision Arena rank #4 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #8 | 87reasoning proxy | Not listedText Arena | 1,493Docs Arena rank #5 | Not listedVision Arena | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #9 | 84reasoning proxy | 1,492Text Arena rank #7 | 1,493Docs Arena rank #6 | 1,290Vision Arena rank #9 | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #10 | 81reasoning proxy | Not listedText Arena | 1,487Docs Arena rank #7 | Not listedVision Arena | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #11 | 80reasoning proxy | 1,491Text Arena rank #9 | Not listedDocs Arena | Not listedVision Arena | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #12 | 80reasoning proxy | 1,492Text Arena rank #8 | 1,483Docs Arena rank #8 | 1,279Vision Arena rank #22 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #13 | 78reasoning proxy | 1,489Text Arena rank #10 | Not listedDocs Arena | Not listedVision Arena | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #14 | 76reasoning proxy | 1,488Text Arena rank #12 | Not listedDocs Arena | Not listedVision Arena | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #15 | 75reasoning proxy | 1,488Text Arena rank #11 | 1,466Docs Arena rank #18 | 1,294Vision Arena rank #6 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #16 | 75reasoning proxy | 1,479Text Arena rank #20 | Not listedDocs Arena | 1,300Vision Arena rank #3 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #17 | 74reasoning proxy | 1,483Text Arena rank #16 | 1,481Docs Arena rank #11 | 1,282Vision Arena rank #17 | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #18 | 74reasoning proxy | 1,482Text Arena rank #18 | Not listedDocs Arena | 1,285Vision Arena rank #12 | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #19 | 73reasoning proxy | 1,482Text Arena rank #17 | 1,478Docs Arena rank #13 | 1,284Vision Arena rank #15 | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #20 | 72reasoning proxy | 1,480Text Arena rank #19 | Not listedDocs Arena | 1,285Vision Arena rank #13 | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #21 | 71reasoning proxy | 1,479Text Arena rank #21 | Not listedDocs Arena | 1,284Vision Arena rank #14 | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #22 | 71reasoning proxy | 1,487Text Arena rank #13 | 1,460Docs Arena rank #22 | 1,278Vision Arena rank #24 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #23 | 70reasoning proxy | 1,483Text Arena rank #15 | Not listedDocs Arena | Not listedVision Arena | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #24 | 70reasoning proxy | 1,477Text Arena rank #22 | 1,475Docs Arena rank #15 | 1,286Vision Arena rank #11 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #25 | 70reasoning proxy | 1,486Text Arena rank #14 | 1,451Docs Arena rank #24 | 1,289Vision Arena rank #10 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #26 | 68reasoning proxy | 1,473Text Arena rank #31 | 1,482Docs Arena rank #10 | 1,279Vision Arena rank #21 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #27 | 68reasoning proxy | 1,476Text Arena rank #23 | Not listedDocs Arena | 1,281Vision Arena rank #19 | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #28 | 68reasoning proxy | 1,476Text Arena rank #24 | Not listedDocs Arena | 1,279Vision Arena rank #23 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #29 | 66reasoning proxy | 1,472Text Arena rank #33 | 1,478Docs Arena rank #14 | 1,275Vision Arena rank #26 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #30 | 65reasoning proxy | 1,474Text Arena rank #27 | Not listedDocs Arena | 1,273Vision Arena rank #27 | Standardmode signal | Text ArenaDocs ArenaVision Arena |
Benchmark guide
What the scores mean.
A quick reading key for reasoning and knowledge rankings while dedicated reasoning benchmark feeds are being integrated.
What does the reasoning proxy measure?
The reasoning proxy currently blends Text, Document, and Vision Arena scores. It is an orientation layer for broad model capability, not a replacement for dedicated reasoning benchmarks like LiveBench, GPQA, AIME, or MMLU-Pro.
Why use Arena scores for reasoning?
Arena scores are live public signals with broad model coverage. They are useful while dedicated reasoning feeds are being wired, but they should be read as preference-based capability signals rather than exam-style accuracy scores.
What will LiveBench add?
LiveBench is designed to update over time and reduce benchmark contamination risk. Once integrated, it can add more direct reasoning, math, data, and coding task signals to this page.
Why are reasoning modes only a signal?
A model name or tag like Thinking, Reasoning, or High can indicate an inference mode, but it is not itself a benchmark score. The page treats those labels as context, not as proof of better reasoning.
