Model comparison
Claude Opus 5 vs GPT-6.1 Sol
Claude Opus 5 is the stronger model overall, scoring 67.8 to 65.6 on the Noometry Index. GPT-6.1 Sol costs 2.5× less per token, which makes it the better buy when Claude Opus 5's lead doesn't matter for your workload.
Last verified . 34 shared benchmarks.
Summary
- They share 34 benchmarks with published results for both. Claude Opus 5 scores higher in 6 categories and GPT-6.1 Sol in 4 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Claude Opus 5 leads 55.6 to 39.6.
- The biggest single-benchmark swing is FrontierMath Tier 4: 73.2% for Claude Opus 5 and 100% for GPT-6.1 Sol.
- GPT-6.1 Sol is cheaper at $2 / $10 per million input/output tokens, against $5 / $25 for Claude Opus 5.
- GPT-6.1 Sol accepts more context: 1.05M tokens versus 1M.
Side by side
| Claude Opus 5 | GPT-6.1 Sol | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 67.8 | 65.6 |
| Released | 2026-07-24 | 2026-09-29 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 128K | 128K |
| Input $ / M tokens | $5 | $2 |
| Output $ / M tokens | $25 | $10 |
| Results tracked | 57 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 5 leads
Claude Opus 5: 67.5 (#5), GPT-6.1 Sol: 63.2 (#8)
| Benchmark | Claude Opus 5 | GPT-6.1 Sol |
|---|---|---|
| DeepSWE | 73.6% | 75.2% |
| FrontierCode | 53.4% | 50.2% |
| LMArena WebDev | 1691 | 1755 |
| SciCode | 56.4% | 55.8% |
| LMArena Coding | 1534 | 1487 |
| CursorBench | 46.6% | — |
| FrontierSWE | 52% | — |
| WeirdML | 91.8% | — |
| ALE-Bench | 2,165 | — |
Agentic & Tool Use Claude Opus 5 leads
Claude Opus 5: 55.6 (#1), GPT-6.1 Sol: 39.6 (#26)
| Benchmark | Claude Opus 5 | GPT-6.1 Sol |
|---|---|---|
| APEX-Agents | 65.8% | 60% |
| GDP.pdf | 24% | 32% |
| OSWorld 2.0 | 31.4% | — |
| τ²-bench Banking | 48.7% | — |
| PostTrainBench | 35% | — |
| BALROG | 63.4% | — |
| GBAEval | 79.6% | — |
| Vending-Bench 2 | 11,182 | — |
Reasoning GPT-6.1 Sol leads
Claude Opus 5: 77.2 (#4), GPT-6.1 Sol: 81.9 (#2)
| Benchmark | Claude Opus 5 | GPT-6.1 Sol |
|---|---|---|
| ARC-AGI-2 | 90.4% | 94.2% |
| NYT Connections (extended) | 94.3% | 95.5% |
| ARC-AGI-1 | 97.5% | 98.5% |
| CritPt | 29.1% | 31.7% |
| Chess Puzzles | 42% | 61% |
| EBR-Bench | 45.7% | 54.3% |
| LMArena Hard Prompts | 1526 | 1466 |
| Mystery Game Puzzles | 59% | 80% |
| Epoch Capabilities Index | 162.78 | 166.09 |
| SimpleBench | 80.6% | — |
| DTBench | 97.9% | — |
| LMCA | 64.5% | — |
| Bench to the Future 3 | 0.12 | — |
Math GPT-6.1 Sol leads
Claude Opus 5: 86.2 (#8), GPT-6.1 Sol: 93.7 (#1)
| Benchmark | Claude Opus 5 | GPT-6.1 Sol |
|---|---|---|
| FrontierMath (Tiers 1-3) | 85.6% | 93.7% |
| FrontierMath Tier 4 | 73.2% | 100% |
| OTIS Mock AIME 2024-2025 | 98.9% | 100% |
| ProofBench | 99% | 99% |
| LMArena Math | 1531 | 1464 |
Knowledge GPT-6.1 Sol leads
Claude Opus 5: 66.8 (#9), GPT-6.1 Sol: 71.8 (#4)
| Benchmark | Claude Opus 5 | GPT-6.1 Sol |
|---|---|---|
| GPQA Diamond | 93.9% | 95.4% |
| SimpleQA Verified | 59.9% | 73.9% |
| LMArena Expert | 1557 | 1502 |
Multimodal GPT-6.1 Sol leads
Claude Opus 5: 50.8 (#8), GPT-6.1 Sol: 52.7 (#5)
| Benchmark | Claude Opus 5 | GPT-6.1 Sol |
|---|---|---|
| LMArena Vision | 1319 | 1288 |
| Furniture Assembly | 60.8% | 80% |
| Blueprint-Bench 2 | 30.4% | — |
| LMArena Document | 1516 | — |
Multilingual Claude Opus 5 leads
Claude Opus 5: 58.8 (#4), GPT-6.1 Sol: 54.3 (#46)
| Benchmark | Claude Opus 5 | GPT-6.1 Sol |
|---|---|---|
| LMArena Non-English | 1501 | 1438 |
| LMArena Chinese | 1574 | 1477 |
| LMArena Russian | 1507 | 1455 |
| LMArena French | 1519 | — |
| LMArena German | 1524 | — |
| LMArena Japanese | 1516 | — |
| LMArena Korean | 1521 | — |
| LMArena Spanish | 1519 | — |
Instruction Following Claude Opus 5 leads
Claude Opus 5: 79.2 (#7), GPT-6.1 Sol: 77.0 (#29)
| Benchmark | Claude Opus 5 | GPT-6.1 Sol |
|---|---|---|
| LMArena Instruction Following | 1517 | 1468 |
Long Context Claude Opus 5 leads
Claude Opus 5: 46.5 (#21), GPT-6.1 Sol: 44.9 (#54)
| Benchmark | Claude Opus 5 | GPT-6.1 Sol |
|---|---|---|
| LMArena Longer Query | 1515 | 1465 |
Writing & Preference Claude Opus 5 leads
Claude Opus 5: 79.2 (#1), GPT-6.1 Sol: 63.6 (#63)
| Benchmark | Claude Opus 5 | GPT-6.1 Sol |
|---|---|---|
| LMArena Text | 1507 | 1447 |
| LMArena Creative Writing | 1491 | 1432 |
| LMArena Multi-Turn | 1499 | 1449 |
| EQ-Bench Creative Writing | 2133 | — |
| EQ-Bench 4 | 1385 | — |
Frequently asked questions
Is Claude Opus 5 better than GPT-6.1 Sol?
Claude Opus 5 is the stronger model overall, scoring 67.8 to 65.6 on the Noometry Index. GPT-6.1 Sol costs 2.5× less per token, which makes it the better buy when Claude Opus 5's lead doesn't matter for your workload.
Which is cheaper, Claude Opus 5 or GPT-6.1 Sol?
GPT-6.1 Sol is cheaper. It lists at $2 per million input tokens and $10 per million output tokens; Claude Opus 5 lists at $5 and $25.
Is Claude Opus 5 or GPT-6.1 Sol better for coding?
Claude Opus 5 scores higher on coding benchmarks: 67.5 versus 63.2 in the Noometry coding category.
Which has the bigger context window?
GPT-6.1 Sol does, with 1.05M tokens against 1M.
How many benchmarks do Claude Opus 5 and GPT-6.1 Sol share?
34 benchmarks have published results for both models. Claude Opus 5 has 57 scored results on Noometry and GPT-6.1 Sol has 34.