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
141
Text, docs, or vision signal
Reasoning variants
69
Models tagged from public names
Top proxy
Claude Fable 5 High
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 141
| Rank | Model | Index | Text | Docs | Vision | Mode | Sources |
|---|---|---|---|---|---|---|---|
| #1 | 100reasoning proxy | Not listedText Arena | Not listedDocs Arena | 1,308Vision Arena rank #1 | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #2 | 100reasoning proxy | 1,524Text Arena rank #1 | Not listedDocs Arena | Not listedVision Arena | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #3 | 94reasoning proxy | Not listedText Arena | 1,495Docs Arena rank #2 | 1,299Vision Arena rank #3 | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #4 | 93reasoning proxy | Not listedText Arena | 1,494Docs Arena rank #3 | 1,298Vision Arena rank #4 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #5 | 93reasoning proxy | Not listedText Arena | 1,493Docs Arena rank #5 | 1,298Vision Arena rank #5 | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #6 | 92reasoning proxy | Not listedText Arena | 1,494Docs Arena rank #4 | 1,294Vision Arena rank #7 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #7 | 91reasoning proxy | Not listedText Arena | Not listedDocs Arena | 1,297Vision Arena rank #6 | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #8 | 88reasoning proxy | Not listedText Arena | 1,493Docs Arena rank #6 | 1,286Vision Arena rank #17 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #9 | 88reasoning proxy | Not listedText Arena | Not listedDocs Arena | 1,293Vision Arena rank #11 | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #10 | 87reasoning proxy | Not listedText Arena | 1,490Docs Arena rank #7 | 1,287Vision Arena rank #15 | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #11 | 85reasoning proxy | 1,504Text Arena rank #4 | 1,499Docs Arena rank #1 | Not listedVision Arena | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #12 | 84reasoning proxy | Not listedText Arena | Not listedDocs Arena | 1,289Vision Arena rank #14 | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #13 | 83reasoning proxy | 1,509Text Arena rank #2 | Not listedDocs Arena | Not listedVision Arena | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #14 | 81reasoning proxy | 1,508Text Arena rank #3 | Not listedDocs Arena | Not listedVision Arena | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #15 | 77reasoning proxy | Not listedText Arena | 1,468Docs Arena rank #19 | 1,290Vision Arena rank #12 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #16 | 74reasoning proxy | 1,502Text Arena rank #6 | Not listedDocs Arena | Not listedVision Arena | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #17 | 72reasoning proxy | 1,493Text Arena rank #12 | Not listedDocs Arena | 1,293Vision Arena rank #10 | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #18 | 71reasoning proxy | 1,485Text Arena rank #21 | 1,489Docs Arena rank #8 | 1,287Vision Arena rank #16 | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #19 | 71reasoning proxy | 1,494Text Arena rank #10 | Not listedDocs Arena | 1,286Vision Arena rank #18 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #20 | 70reasoning proxy | 1,490Text Arena rank #13 | 1,479Docs Arena rank #12 | 1,280Vision Arena rank #28 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #21 | 69reasoning proxy | 1,489Text Arena rank #16 | 1,467Docs Arena rank #20 | 1,294Vision Arena rank #9 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #22 | 69reasoning proxy | 1,497Text Arena rank #8 | Not listedDocs Arena | Not listedVision Arena | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #23 | 68reasoning proxy | 1,481Text Arena rank #25 | 1,486Docs Arena rank #9 | 1,286Vision Arena rank #21 | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #24 | 67reasoning proxy | 1,496Text Arena rank #9 | Not listedDocs Arena | Not listedVision Arena | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #25 | 66reasoning proxy | 1,482Text Arena rank #24 | Not listedDocs Arena | 1,301Vision Arena rank #2 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #26 | 66reasoning proxy | 1,484Text Arena rank #22 | Not listedDocs Arena | 1,294Vision Arena rank #8 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #27 | 65reasoning proxy | 1,481Text Arena rank #26 | 1,480Docs Arena rank #11 | 1,281Vision Arena rank #25 | Reasoningmode signal | Text ArenaDocs ArenaVision Arena | |
| #28 | 65reasoning proxy | 1,494Text Arena rank #11 | Not listedDocs Arena | Not listedVision Arena | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #29 | 65reasoning proxy | 1,477Text Arena rank #31 | 1,483Docs Arena rank #10 | 1,286Vision Arena rank #20 | Standardmode signal | Text ArenaDocs ArenaVision Arena | |
| #30 | 63reasoning proxy | 1,487Text Arena rank #19 | 1,459Docs Arena rank #27 | 1,280Vision Arena rank #29 | 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.
