Model comparison
Claude Opus 4.8 vs GPT-6 Sol
GPT-6 Sol is the stronger model overall, scoring 61.8 to 60.7 on the Noometry Index.
Last verified . 44 shared benchmarks.
Summary
- They share 44 benchmarks with published results for both. Claude Opus 4.8 scores higher in 5 categories and GPT-6 Sol in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Claude Opus 4.8 leads 47.6 to 37.2.
- The biggest single-benchmark swing is FrontierMath Tier 4: 56.1% for Claude Opus 4.8 and 90% for GPT-6 Sol.
- GPT-6 Sol is cheaper at $2 / $10 per million input/output tokens, against $5 / $25 for Claude Opus 4.8.
- GPT-6 Sol accepts more context: 1.05M tokens versus 1M.
Side by side
| Claude Opus 4.8 | GPT-6 Sol | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 60.7 | 61.8 |
| Released | 2026-05-28 | 2026-09-22 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 128K | 128K |
| Input $ / M tokens | $5 | $2 |
| Output $ / M tokens | $25 | $10 |
| Results tracked | 65 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Claude Opus 4.8: 59.9 (#12), GPT-6 Sol: 60.1 (#11)
| Benchmark | Claude Opus 4.8 | GPT-6 Sol |
|---|---|---|
| DeepSWE | 59% | 68.8% |
| FrontierCode | 46.5% | 49.3% |
| LMArena WebDev | 1556 | 1688 |
| SciCode | 53.5% | 57.6% |
| LMArena Coding | 1490 | 1447 |
| ALE-Bench | 1,564 | 2,462 |
| GSO | 47.1% | — |
| WeirdML | 82.9% | — |
Agentic & Tool Use Claude Opus 4.8 leads
Claude Opus 4.8: 47.6 (#11), GPT-6 Sol: 37.2 (#36)
| Benchmark | Claude Opus 4.8 | GPT-6 Sol |
|---|---|---|
| APEX-Agents | 48.9% | 54.3% |
| GDP.pdf | 24% | 26.4% |
| Vending-Bench 2 | 5,787 | 14,428 |
| OSWorld 2.0 | 20.6% | — |
| Remote Labor Index | 8.3% | — |
| τ²-bench Banking | 39.7% | — |
| DeepResearch Bench | 50.2% | — |
| PostTrainBench | 33.8% | — |
| GBAEval | 70.9% | — |
| LMArena Search | 1204 | — |
Reasoning GPT-6 Sol leads
Claude Opus 4.8: 64.7 (#16), GPT-6 Sol: 74.0 (#9)
| Benchmark | Claude Opus 4.8 | GPT-6 Sol |
|---|---|---|
| ARC-AGI-2 | 72.1% | 89.6% |
| NYT Connections (extended) | 91.1% | 90.1% |
| ARC-AGI-1 | 92.5% | 95.5% |
| CritPt | 20.9% | 30.9% |
| EBR-Bench | 28.6% | 53.3% |
| LMArena Hard Prompts | 1482 | 1418 |
| Mystery Game Puzzles | 36% | 56% |
| DTBench | 94.9% | 97.3% |
| LMCA | 57.5% | 59.1% |
| Epoch Capabilities Index | 158.21 | 162.72 |
| SimpleBench | 64.8% | — |
| Kagi LLM Benchmark | 88.8% | — |
| Chess Puzzles | 34% | — |
| EnigmaEval | 23.5% | — |
| Surface Evolver Bench | 87.5% | — |
| Bench to the Future 3 | 0.14 | — |
| ForecastBench | 59.9 | — |
Math GPT-6 Sol leads
Claude Opus 4.8: 78.4 (#13), GPT-6 Sol: 87.2 (#7)
| Benchmark | Claude Opus 4.8 | GPT-6 Sol |
|---|---|---|
| FrontierMath (Tiers 1-3) | 80% | 89.8% |
| FrontierMath Tier 4 | 56.1% | 90% |
| OTIS Mock AIME 2024-2025 | 98.3% | 100% |
| ProofBench | 69% | 83% |
| LMArena Math | 1487 | 1402 |
| MathArena Final-Answer Competitions | 91.8% | — |
| FrontierMath (Feb 2025 set) | 47.2% | — |
| FrontierMath Tier 4 (v1) | 31.3% | — |
Knowledge GPT-6 Sol leads
Claude Opus 4.8: 61.3 (#29), GPT-6 Sol: 64.8 (#15)
| Benchmark | Claude Opus 4.8 | GPT-6 Sol |
|---|---|---|
| GPQA Diamond | 91% | 94.3% |
| SimpleQA Verified | 53% | 60.7% |
| LMArena Expert | 1502 | 1439 |
| Vectara Hallucination Rate | — | 6.5% |
Multimodal GPT-6 Sol leads
Claude Opus 4.8: 42.9 (#26), GPT-6 Sol: 47.6 (#10)
| Benchmark | Claude Opus 4.8 | GPT-6 Sol |
|---|---|---|
| LMArena Vision | 1294 | 1245 |
| Blueprint-Bench 2 | 14.5% | 36.9% |
| Furniture Assembly | 42.5% | 58.3% |
| LMArena Document | 1475 | — |
Multilingual Claude Opus 4.8 leads
Claude Opus 4.8: 55.2 (#33), GPT-6 Sol: 50.5 (#118)
| Benchmark | Claude Opus 4.8 | GPT-6 Sol |
|---|---|---|
| LMArena Non-English | 1450 | 1385 |
| LMArena Chinese | 1507 | 1405 |
| LMArena French | 1481 | 1410 |
| LMArena German | 1472 | 1390 |
| LMArena Japanese | 1440 | 1385 |
| LMArena Korean | 1432 | 1341 |
| LMArena Russian | 1474 | 1401 |
| LMArena Spanish | 1466 | 1384 |
Instruction Following Claude Opus 4.8 leads
Claude Opus 4.8: 77.4 (#24), GPT-6 Sol: 74.5 (#94)
| Benchmark | Claude Opus 4.8 | GPT-6 Sol |
|---|---|---|
| LMArena Instruction Following | 1476 | 1412 |
Long Context Claude Opus 4.8 leads
Claude Opus 4.8: 45.4 (#35), GPT-6 Sol: 43.1 (#108)
| Benchmark | Claude Opus 4.8 | GPT-6 Sol |
|---|---|---|
| LMArena Longer Query | 1483 | 1411 |
Writing & Preference Too close to call
Claude Opus 4.8: 72.0 (#16), GPT-6 Sol: 71.9 (#18)
| Benchmark | Claude Opus 4.8 | GPT-6 Sol |
|---|---|---|
| LMArena Text | 1461 | 1395 |
| LMArena Creative Writing | 1454 | 1378 |
| EQ-Bench Creative Writing | 1840 | 2125 |
| LMArena Multi-Turn | 1476 | 1412 |
| EQ-Bench 4 | 1281 | — |
Frequently asked questions
Is Claude Opus 4.8 better than GPT-6 Sol?
GPT-6 Sol is the stronger model overall, scoring 61.8 to 60.7 on the Noometry Index.
Which is cheaper, Claude Opus 4.8 or GPT-6 Sol?
GPT-6 Sol is cheaper. It lists at $2 per million input tokens and $10 per million output tokens; Claude Opus 4.8 lists at $5 and $25.
Is Claude Opus 4.8 or GPT-6 Sol better for coding?
They score almost the same on coding (59.9 vs 60.1); test both on your own repository before choosing.
Which has the bigger context window?
GPT-6 Sol does, with 1.05M tokens against 1M.
How many benchmarks do Claude Opus 4.8 and GPT-6 Sol share?
44 benchmarks have published results for both models. Claude Opus 4.8 has 65 scored results on Noometry and GPT-6 Sol has 45.