Model comparison
AI Co-Mathematician vs Claude Opus 5.5
Claude Opus 5.5 has enough public results to be ranked (#3); AI Co-Mathematician does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
GoogleSummary
- They share 1 benchmark with published results for both. AI Co-Mathematician scores higher in 0 categories and Claude Opus 5.5 in 1 category; one gap is clear of the uncertainty.
- The widest gap is in math, where Claude Opus 5.5 leads 92.4 to 71.7.
- The biggest single-benchmark swing is FrontierMath Tier 4: 75.6% for AI Co-Mathematician and 95% for Claude Opus 5.5.
Side by side
| AI Co-Mathematician | Claude Opus 5.5 | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 57.6 | 68.5 |
| Released | 2026-05-08 | 2026-09-22 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1M |
| Max output | — | 128K |
| Input $ / M tokens | — | $4 |
| Output $ / M tokens | — | $20 |
| Results tracked | 2 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
AI Co-Mathematician: —, Claude Opus 5.5: 71.4 (#1)
| Benchmark | AI Co-Mathematician | Claude Opus 5.5 |
|---|---|---|
| FrontierCode | — | 54.4% |
| CursorBench | — | 57.8% |
| LMArena WebDev | — | 1820 |
| FrontierSWE | — | 62.3% |
| SciCode | — | 66.9% |
| LMArena Coding | — | 1545 |
| MirrorCode | — | 77.4% |
Agentic & Tool Use Not comparable
AI Co-Mathematician: —, Claude Opus 5.5: 45.3 (#13)
| Benchmark | AI Co-Mathematician | Claude Opus 5.5 |
|---|---|---|
| APEX-Agents | — | 73.5% |
| GDP.pdf | — | 30.6% |
Reasoning Not comparable
AI Co-Mathematician: —, Claude Opus 5.5: 79.5 (#2)
| Benchmark | AI Co-Mathematician | Claude Opus 5.5 |
|---|---|---|
| ARC-AGI-2 | — | 92.5% |
| NYT Connections (extended) | — | 88.5% |
| ARC-AGI-1 | — | 97.5% |
| CritPt | — | 31.7% |
| EBR-Bench | — | 71.4% |
| LMArena Hard Prompts | — | 1545 |
| Mystery Game Puzzles | — | 71% |
| DTBench | — | 98.9% |
| LMCA | — | 68.2% |
Math Claude Opus 5.5 leads
AI Co-Mathematician: 71.7, Claude Opus 5.5: 92.4 (#2)
| Benchmark | AI Co-Mathematician | Claude Opus 5.5 |
|---|---|---|
| FrontierMath Tier 4 | 75.6% | 95% |
| FrontierMath (Tiers 1-3) | — | 91.2% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 100% |
| FrontierMath Tier 4 (v1) | 47.9% | — |
Knowledge Not comparable
AI Co-Mathematician: —, Claude Opus 5.5: 66.6 (#9)
| Benchmark | AI Co-Mathematician | Claude Opus 5.5 |
|---|---|---|
| GPQA Diamond | — | 90.6% |
| SimpleQA Verified | — | 72.2% |
| LMArena Expert | — | 1564 |
Multimodal Not comparable
AI Co-Mathematician: —, Claude Opus 5.5: 56.5 (#2)
| Benchmark | AI Co-Mathematician | Claude Opus 5.5 |
|---|---|---|
| Furniture Assembly | — | 83.3% |
Multilingual Not comparable
AI Co-Mathematician: —, Claude Opus 5.5: 59.8 (#1)
| Benchmark | AI Co-Mathematician | Claude Opus 5.5 |
|---|---|---|
| LMArena Non-English | — | 1513 |
| LMArena Chinese | — | 1572 |
| LMArena Russian | — | 1532 |
Instruction Following Not comparable
AI Co-Mathematician: —, Claude Opus 5.5: 80.1 (#2)
| Benchmark | AI Co-Mathematician | Claude Opus 5.5 |
|---|---|---|
| LMArena Instruction Following | — | 1535 |
Long Context Not comparable
AI Co-Mathematician: —, Claude Opus 5.5: 47.3 (#18)
| Benchmark | AI Co-Mathematician | Claude Opus 5.5 |
|---|---|---|
| LMArena Longer Query | — | 1540 |
Writing & Preference Not comparable
AI Co-Mathematician: —, Claude Opus 5.5: 78.7 (#3)
| Benchmark | AI Co-Mathematician | Claude Opus 5.5 |
|---|---|---|
| LMArena Text | — | 1518 |
| LMArena Creative Writing | — | 1538 |
| EQ-Bench Creative Writing | — | 2050 |
| LMArena Multi-Turn | — | 1520 |
Frequently asked questions
Is AI Co-Mathematician better than Claude Opus 5.5?
Claude Opus 5.5 has enough public results to be ranked (#3); AI Co-Mathematician does not yet, so treat this comparison as directional.
How many benchmarks do AI Co-Mathematician and Claude Opus 5.5 share?
1 benchmark has published results for both models. AI Co-Mathematician has 2 scored results on Noometry and Claude Opus 5.5 has 35.