Model comparison
Claude Opus 4.1 vs GPT-5
GPT-5 is the stronger model overall, scoring 50.9 to 41.0 on the Noometry Index.
Last verified . 47 shared benchmarks.
Summary
- They share 47 benchmarks with published results for both. Claude Opus 4.1 scores higher in 3 categories and GPT-5 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5 leads 55.0 to 22.3.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 12.6% for Claude Opus 4.1 and 55.4% for GPT-5.
- GPT-5 is cheaper at $1.25 / $10 per million input/output tokens, against $15 / $75 for Claude Opus 4.1.
- GPT-5 accepts more context: 400K tokens versus 200K.
Side by side
| Claude Opus 4.1 | GPT-5 | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 41.0 | 50.9 |
| Released | 2025-08-05 | 2025-08-07 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 400K |
| Max output | 32K | 128K |
| Input $ / M tokens | $15 | $1.25 |
| Output $ / M tokens | $75 | $10 |
| Results tracked | 48 | 69 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 leads
Claude Opus 4.1: 44.4 (#73), GPT-5: 50.3 (#47)
| Benchmark | Claude Opus 4.1 | GPT-5 |
|---|---|---|
| SWE-bench Verified | 73.3% | 73.6% |
| LMArena WebDev | 1390 | 1418 |
| WeirdML | 45.9% | 60.7% |
| LMArena Coding | 1479 | 1436 |
| ALE-Bench | 674.77 | 1,162 |
| AlgoTune | 1.34 | 1.67 |
| SWE-bench Verified (bash only) | — | 65% |
| Aider Polyglot | — | 88% |
| SciCode | — | 42.9% |
| GSO | — | 6.9% |
Agentic & Tool Use Claude Opus 4.1 leads
Claude Opus 4.1: 35.0 (#41), GPT-5: 33.1 (#56)
| Benchmark | Claude Opus 4.1 | GPT-5 |
|---|---|---|
| Terminal-Bench | 38% | 49.6% |
| GDPval | 43.6% | 34.8% |
| DeepResearch Bench | 48.3% | 49.6% |
| LMArena Search | 1148 | 1133 |
| METR Time Horizons | 66.8% | 69.6% |
| Remote Labor Index | — | 1.7% |
| Cybench | 42% | — |
| BALROG | — | 32.8% |
Reasoning GPT-5 leads
Claude Opus 4.1: 32.2 (#76), GPT-5: 38.3 (#64)
| Benchmark | Claude Opus 4.1 | GPT-5 |
|---|---|---|
| SimpleBench | 60% | 56.7% |
| Chess Puzzles | 7% | 37% |
| EnigmaEval | 7.2% | 10.5% |
| EBR-Bench | 7.9% | 12.7% |
| LMArena Hard Prompts | 1443 | 1416 |
| Mystery Game Puzzles | 21% | 23% |
| DTBench | 80% | 90.7% |
| LMCA | 37.1% | 40% |
| Epoch Capabilities Index | 144.12 | 150 |
| ForecastBench | 62 | 61.4 |
| ARC-AGI-2 | — | 9.9% |
| Kagi LLM Benchmark | — | 72.7% |
| ARC-AGI-1 | — | 65.7% |
| CritPt | — | 12.6% |
Math GPT-5 leads
Claude Opus 4.1: 22.3 (#277), GPT-5: 55.0 (#44)
| Benchmark | Claude Opus 4.1 | GPT-5 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 12.6% | 55.4% |
| FrontierMath Tier 4 | 2.4% | 22% |
| OTIS Mock AIME 2024-2025 | 68.9% | 91.4% |
| LMArena Math | 1431 | 1407 |
| FrontierMath (Feb 2025 set) | 7.2% | 32.4% |
| FrontierMath Tier 4 (v1) | 4.2% | 12.5% |
| ProofBench | — | 18% |
| Omni-MATH | — | 64.7% |
| MATH Level 5 | — | 98.1% |
Knowledge GPT-5 leads
Claude Opus 4.1: 42.0 (#101), GPT-5: 56.6 (#43)
| Benchmark | Claude Opus 4.1 | GPT-5 |
|---|---|---|
| GPQA Diamond | 77.3% | 86.2% |
| Humanity's Last Exam | 11.5% | 25.3% |
| Confabulations | 17.1% | 10.3% |
| Vectara Hallucination Rate | 11.8% | 14.7% |
| LMArena Expert | 1439 | 1419 |
| SimpleQA Verified | — | 50.1% |
| MMLU-Pro | — | 86.3% |
| GPQA (HELM) | — | 79.2% |
Multimodal GPT-5 leads
Claude Opus 4.1: 26.8 (#119), GPT-5: 46.8 (#13)
| Benchmark | Claude Opus 4.1 | GPT-5 |
|---|---|---|
| VPCT | 35% | 66% |
| LMArena Vision | — | 1232 |
| GeoBench | — | 81% |
Multilingual Too close to call
Claude Opus 4.1: 52.0 (#95), GPT-5: 51.4 (#110)
| Benchmark | Claude Opus 4.1 | GPT-5 |
|---|---|---|
| LMArena Non-English | 1405 | 1397 |
| LMArena Chinese | 1427 | 1422 |
| LMArena French | 1431 | 1410 |
| LMArena German | 1413 | 1416 |
| LMArena Japanese | 1378 | 1409 |
| LMArena Korean | 1380 | 1360 |
| LMArena Russian | 1422 | 1406 |
| LMArena Spanish | 1448 | 1399 |
Instruction Following Claude Opus 4.1 leads
Claude Opus 4.1: 75.6 (#58), GPT-5: 73.8 (#113)
| Benchmark | Claude Opus 4.1 | GPT-5 |
|---|---|---|
| LMArena Instruction Following | 1435 | 1388 |
| IFEval | — | 87.5% |
Long Context GPT-5 leads
Claude Opus 4.1: 44.5 (#63), GPT-5: 69.5 (#2)
| Benchmark | Claude Opus 4.1 | GPT-5 |
|---|---|---|
| LMArena Longer Query | 1455 | 1399 |
| Fiction.LiveBench | — | 97.2% |
Writing & Preference Too close to call
Claude Opus 4.1: 62.4 (#74), GPT-5: 63.4 (#65)
| Benchmark | Claude Opus 4.1 | GPT-5 |
|---|---|---|
| LMArena Text | 1419 | 1406 |
| LMArena Creative Writing | 1412 | 1365 |
| Short-Story Creative Writing | 84.7% | 86% |
| LMArena Multi-Turn | 1444 | 1426 |
| EQ-Bench Creative Writing | — | 1627 |
| WildBench | — | 85.7% |
Frequently asked questions
Is Claude Opus 4.1 better than GPT-5?
GPT-5 is the stronger model overall, scoring 50.9 to 41.0 on the Noometry Index.
Which is cheaper, Claude Opus 4.1 or GPT-5?
GPT-5 is cheaper. It lists at $1.25 per million input tokens and $10 per million output tokens; Claude Opus 4.1 lists at $15 and $75.
Is Claude Opus 4.1 or GPT-5 better for coding?
GPT-5 scores higher on coding benchmarks: 50.3 versus 44.4 in the Noometry coding category.
Which has the bigger context window?
GPT-5 does, with 400K tokens against 200K.
How many benchmarks do Claude Opus 4.1 and GPT-5 share?
47 benchmarks have published results for both models. Claude Opus 4.1 has 48 scored results on Noometry and GPT-5 has 69.