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
148
Text, docs, or vision signal
Reasoning variants
43
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 148
| Rank | Model | Index | Text | Docs | Vision | Mode | Sources |
|---|---|---|---|---|---|---|---|
| #1 | 100reasoning proxy | 1,507Text Arena rank #1 | 1,509Docs Arena rank #1 | 1,318Vision Arena rank #1 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #2 | 94reasoning proxy | 1,502Text Arena rank #3 | 1,503Docs Arena rank #2 | 1,304Vision Arena rank #2 | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #3 | 92reasoning proxy | 1,504Text Arena rank #2 | 1,494Docs Arena rank #4 | 1,299Vision Arena rank #3 | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #4 | 88reasoning proxy | 1,494Text Arena rank #5 | 1,500Docs Arena rank #3 | 1,299Vision Arena rank #4 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #5 | 88reasoning proxy | 1,498Text Arena rank #4 | 1,491Docs Arena rank #5 | 1,298Vision Arena rank #5 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #6 | 84reasoning proxy | 1,493Text Arena rank #6 | Not listedDocs Arena | Not listedVision Arena | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #7 | 78reasoning proxy | 1,483Text Arena rank #12 | 1,487Docs Arena rank #6 | 1,286Vision Arena rank #9 | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #8 | 76reasoning proxy | 1,487Text Arena rank #7 | 1,469Docs Arena rank #13 | 1,295Vision Arena rank #6 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #9 | 76reasoning proxy | 1,486Text Arena rank #10 | Not listedDocs Arena | Not listedVision Arena | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #10 | 76reasoning proxy | 1,486Text Arena rank #8 | Not listedDocs Arena | Not listedVision Arena | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #11 | 75reasoning proxy | 1,482Text Arena rank #13 | 1,480Docs Arena rank #8 | 1,286Vision Arena rank #8 | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #12 | 72reasoning proxy | 1,478Text Arena rank #14 | Not listedDocs Arena | 1,281Vision Arena rank #13 | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #13 | 72reasoning proxy | 1,476Text Arena rank #16 | 1,482Docs Arena rank #7 | 1,282Vision Arena rank #12 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #14 | 71reasoning proxy | 1,486Text Arena rank #9 | 1,452Docs Arena rank #19 | 1,289Vision Arena rank #7 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #15 | 70reasoning proxy | 1,476Text Arena rank #17 | Not listedDocs Arena | 1,279Vision Arena rank #14 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #16 | 70reasoning proxy | 1,485Text Arena rank #11 | 1,456Docs Arena rank #17 | 1,278Vision Arena rank #15 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #17 | 70reasoning proxy | 1,476Text Arena rank #15 | Not listedDocs Arena | 1,276Vision Arena rank #18 | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #18 | 70reasoning proxy | 1,475Text Arena rank #19 | 1,474Docs Arena rank #11 | 1,285Vision Arena rank #11 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #19 | 69reasoning proxy | 1,472Text Arena rank #26 | 1,480Docs Arena rank #9 | 1,276Vision Arena rank #17 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #20 | 66reasoning proxy | 1,474Text Arena rank #20 | 1,460Docs Arena rank #15 | 1,286Vision Arena rank #10 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #21 | 64reasoning proxy | 1,475Text Arena rank #18 | Not listedDocs Arena | Not listedVision Arena | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #22 | 64reasoning proxy | 1,473Text Arena rank #23 | 1,457Docs Arena rank #16 | 1,276Vision Arena rank #19 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #23 | 63reasoning proxy | 1,466Text Arena rank #32 | 1,471Docs Arena rank #12 | 1,278Vision Arena rank #16 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #24 | 63reasoning proxy | 1,474Text Arena rank #21 | Not listedDocs Arena | Not listedVision Arena | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #25 | 62reasoning proxy | 1,473Text Arena rank #25 | Not listedDocs Arena | Not listedVision Arena | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #26 | 61reasoning proxy | 1,470Text Arena rank #28 | Not listedDocs Arena | 1,250Vision Arena rank #29 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #27 | 61reasoning proxy | 1,462Text Arena rank #37 | 1,477Docs Arena rank #10 | 1,264Vision Arena rank #22 | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #28 | 60reasoning proxy | 1,471Text Arena rank #27 | Not listedDocs Arena | Not listedVision Arena | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #29 | 57reasoning proxy | 1,469Text Arena rank #29 | 1,463Docs Arena rank #14 | Not listedVision Arena | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #30 | 57reasoning proxy | 1,473Text Arena rank #24 | 1,441Docs Arena rank #24 | 1,253Vision Arena rank #28 | Reasoningmode 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.
