Model comparison
Claude 3 Opus vs GPT-4o
Claude 3 Opus and GPT-4o score almost the same on the Noometry Index (29.5 vs 28.6), so choose on price, context window or the category you care about most.
Last verified . 45 shared benchmarks.
Summary
- They share 45 benchmarks with published results for both. Claude 3 Opus scores higher in 4 categories and GPT-4o in 6 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in coding, where Claude 3 Opus leads 32.9 to 24.8.
- The biggest single-benchmark swing is MATH Level 5: 37.5% for Claude 3 Opus and 53.3% for GPT-4o.
Side by side
| Claude 3 Opus | GPT-4o | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 29.5 | 28.6 |
| Released | 2024-02-29 | 2024-05-13 |
| Weights | Proprietary | Proprietary |
| Context window | — | 128K |
| Max output | — | 16K |
| Input $ / M tokens | — | $2.50 |
| Output $ / M tokens | — | $10 |
| Results tracked | 46 | 72 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude 3 Opus leads
Claude 3 Opus: 32.9 (#267), GPT-4o: 24.8 (#328)
| Benchmark | Claude 3 Opus | GPT-4o |
|---|---|---|
| WeirdML | 19.2% | 25.1% |
| BigCodeBench Instruct | 45.5% | 51.1% |
| LiveBench Coding | 38.6% | 51.4% |
| LMArena Coding | 1264 | 1297 |
| BigCodeBench Complete | 57.4% | 61.1% |
| HumanEval+ | 77.4% | 87.2% |
| MBPP+ | 73.3% | 72.2% |
| SWE-bench Verified | — | 31% |
| SWE-bench Verified (bash only) | — | 21.6% |
| Aider Polyglot | — | 45.3% |
| GSO | — | 0% |
| CadEval | — | 26% |
Agentic & Tool Use Claude 3 Opus leads
Claude 3 Opus: 24.6 (#116), GPT-4o: 21.0 (#141)
| Benchmark | Claude 3 Opus | GPT-4o |
|---|---|---|
| Cybench | 10% | 12.5% |
| METR Time Horizons | 29.5% | 40.8% |
| GDPval | — | 9.9% |
| TheAgentCompany | — | 8.6% |
| BALROG | — | 32.3% |
| LMArena Search | — | 1006 |
Reasoning Claude 3 Opus leads
Claude 3 Opus: 14.6 (#324), GPT-4o: 9.4 (#343)
| Benchmark | Claude 3 Opus | GPT-4o |
|---|---|---|
| SimpleBench | 23.5% | 17.8% |
| Chess Puzzles | 5% | 13% |
| EnigmaEval | 0.8% | 0.8% |
| LiveBench Reasoning | 40.6% | 55.8% |
| LMArena Hard Prompts | 1245 | 1281 |
| DTBench | 61.6% | 64.5% |
| LiveBench Data Analysis | 57.9% | 60.9% |
| LMCA | 17% | 16.6% |
| Epoch Capabilities Index | 126.91 | 128.97 |
| ForecastBench | 58.4 | 57.7 |
| LiveBench | 49.2% | 55.3% |
| ARC-AGI-2 | — | 0% |
| ARC-AGI-1 | — | 4.5% |
| CritPt | — | 0% |
| WinoGrande | 88.5% | — |
Math Claude 3 Opus leads
Claude 3 Opus: 14.8 (#299), GPT-4o: 10.6 (#312)
| Benchmark | Claude 3 Opus | GPT-4o |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.7% | 6.4% |
| LiveBench Math | 43.6% | 49.5% |
| LMArena Math | 1273 | 1285 |
| MATH Level 5 | 37.5% | 53.3% |
| FrontierMath (Tiers 1-3) | — | 0.4% |
| Omni-MATH | — | 29.3% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge GPT-4o leads
Claude 3 Opus: 24.5 (#267), GPT-4o: 28.8 (#242)
| Benchmark | Claude 3 Opus | GPT-4o |
|---|---|---|
| GPQA Diamond | 47.2% | 49.2% |
| SimpleQA Verified | 12.6% | 26% |
| Confabulations | 22.7% | 15.3% |
| LMArena Expert | 1223 | 1250 |
| MMLU | 84.6% | 88.1% |
| Humanity's Last Exam | — | 2.7% |
| MMLU-Pro | — | 71.3% |
| Vectara Hallucination Rate | — | 9.6% |
| GPQA (HELM) | — | 52% |
Multimodal GPT-4o leads
Claude 3 Opus: 27.1 (#116), GPT-4o: 34.5 (#91)
| Benchmark | Claude 3 Opus | GPT-4o |
|---|---|---|
| LMArena Vision | 1023 | 1137 |
| Video-MME | — | 71.9% |
| GeoBench | — | 71% |
| VPCT | — | 40% |
| ScienceQA | — | 88.5% |
Multilingual GPT-4o leads
Claude 3 Opus: 41.4 (#207), GPT-4o: 43.2 (#186)
| Benchmark | Claude 3 Opus | GPT-4o |
|---|---|---|
| LMArena Non-English | 1258 | 1283 |
| LMArena Chinese | 1248 | 1277 |
| LMArena French | 1275 | 1304 |
| LMArena German | 1258 | 1282 |
| LMArena Japanese | 1204 | 1257 |
| LMArena Korean | 1187 | 1234 |
| LMArena Russian | 1280 | 1286 |
| LMArena Spanish | 1246 | 1292 |
Instruction Following GPT-4o leads
Claude 3 Opus: 64.1 (#228), GPT-4o: 66.6 (#207)
| Benchmark | Claude 3 Opus | GPT-4o |
|---|---|---|
| LiveBench Instruction Following | 63.9% | 68.6% |
| LMArena Instruction Following | 1248 | 1278 |
| IFEval | — | 81.7% |
Long Context GPT-4o leads
Claude 3 Opus: 38.2 (#202), GPT-4o: 39.4 (#179)
| Benchmark | Claude 3 Opus | GPT-4o |
|---|---|---|
| LMArena Longer Query | 1259 | 1289 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference GPT-4o leads
Claude 3 Opus: 47.2 (#213), GPT-4o: 52.6 (#166)
| Benchmark | Claude 3 Opus | GPT-4o |
|---|---|---|
| LMArena Text | 1262 | 1300 |
| LMArena Creative Writing | 1235 | 1292 |
| LMArena Multi-Turn | 1275 | 1302 |
| LiveBench Language | 50.4% | 47.6% |
| Short-Story Creative Writing | — | 81.8% |
| WildBench | — | 82.8% |
Frequently asked questions
Is Claude 3 Opus better than GPT-4o?
Claude 3 Opus and GPT-4o score almost the same on the Noometry Index (29.5 vs 28.6), so choose on price, context window or the category you care about most.
Is Claude 3 Opus or GPT-4o better for coding?
Claude 3 Opus scores higher on coding benchmarks: 32.9 versus 24.8 in the Noometry coding category.
How many benchmarks do Claude 3 Opus and GPT-4o share?
45 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and GPT-4o has 72.