Model comparison
Claude 3 Opus vs GPT-5.4 Pro
GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 29.5 on the Noometry Index.
Last verified . 7 shared benchmarks.
Summary
- They share 7 benchmarks with published results for both. Claude 3 Opus scores higher in 0 categories and GPT-5.4 Pro in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.4 Pro leads 72.4 to 14.8.
- The biggest single-benchmark swing is Chess Puzzles: 5% for Claude 3 Opus and 58.6% for GPT-5.4 Pro.
Side by side
| Claude 3 Opus | GPT-5.4 Pro | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 29.5 | 58.9 |
| Released | 2024-02-29 | 2026-03-05 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 128K |
| Input $ / M tokens | — | $30 |
| Output $ / M tokens | — | $180 |
| Results tracked | 46 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 Pro leads
Claude 3 Opus: 32.9 (#267), GPT-5.4 Pro: 43.2 (#90)
| Benchmark | Claude 3 Opus | GPT-5.4 Pro |
|---|---|---|
| WeirdML | 19.2% | 57.4% |
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 38.6% | — |
| LMArena Coding | 1264 | — |
| BigCodeBench Complete | 57.4% | — |
| HumanEval+ | 77.4% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Not comparable
Claude 3 Opus: 24.6 (#116), GPT-5.4 Pro: —
| Benchmark | Claude 3 Opus | GPT-5.4 Pro |
|---|---|---|
| Cybench | 10% | — |
| METR Time Horizons | 29.5% | — |
Reasoning GPT-5.4 Pro leads
Claude 3 Opus: 14.6 (#324), GPT-5.4 Pro: 70.7 (#13)
| Benchmark | Claude 3 Opus | GPT-5.4 Pro |
|---|---|---|
| SimpleBench | 23.5% | 74.1% |
| Chess Puzzles | 5% | 58.6% |
| EnigmaEval | 0.8% | 23.8% |
| Epoch Capabilities Index | 126.91 | 158.93 |
| ARC-AGI-2 | — | 83.3% |
| ARC-AGI-1 | — | 94.5% |
| CritPt | — | 30% |
| LiveBench Reasoning | 40.6% | — |
| LMArena Hard Prompts | 1245 | — |
| DTBench | 61.6% | — |
| LiveBench Data Analysis | 57.9% | — |
| LMCA | 17% | — |
| ForecastBench | 58.4 | — |
| LiveBench | 49.2% | — |
| WinoGrande | 88.5% | — |
Math GPT-5.4 Pro leads
Claude 3 Opus: 14.8 (#299), GPT-5.4 Pro: 72.4 (#22)
| Benchmark | Claude 3 Opus | GPT-5.4 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 82.5% |
| FrontierMath Tier 4 | — | 58.5% |
| OTIS Mock AIME 2024-2025 | 4.7% | — |
| LiveBench Math | 43.6% | — |
| LMArena Math | 1273 | — |
| MATH Level 5 | 37.5% | — |
| FrontierMath (Feb 2025 set) | — | 50% |
| FrontierMath Tier 4 (v1) | — | 37.5% |
Knowledge GPT-5.4 Pro leads
Claude 3 Opus: 24.5 (#267), GPT-5.4 Pro: 68.3 (#7)
| Benchmark | Claude 3 Opus | GPT-5.4 Pro |
|---|---|---|
| GPQA Diamond | 47.2% | 94.6% |
| SimpleQA Verified | 12.6% | 46.3% |
| Humanity's Last Exam | — | 44.3% |
| Confabulations | 22.7% | — |
| Vectara Hallucination Rate | — | 8.3% |
| LMArena Expert | 1223 | — |
| MMLU | 84.6% | — |
Multimodal Not comparable
Claude 3 Opus: 27.1 (#116), GPT-5.4 Pro: —
| Benchmark | Claude 3 Opus | GPT-5.4 Pro |
|---|---|---|
| LMArena Vision | 1023 | — |
Multilingual Not comparable
Claude 3 Opus: 41.4 (#207), GPT-5.4 Pro: —
| Benchmark | Claude 3 Opus | GPT-5.4 Pro |
|---|---|---|
| LMArena Non-English | 1258 | — |
| LMArena Chinese | 1248 | — |
| LMArena French | 1275 | — |
| LMArena German | 1258 | — |
| LMArena Japanese | 1204 | — |
| LMArena Korean | 1187 | — |
| LMArena Russian | 1280 | — |
| LMArena Spanish | 1246 | — |
Instruction Following Not comparable
Claude 3 Opus: 64.1 (#228), GPT-5.4 Pro: —
| Benchmark | Claude 3 Opus | GPT-5.4 Pro |
|---|---|---|
| LiveBench Instruction Following | 63.9% | — |
| LMArena Instruction Following | 1248 | — |
Long Context Not comparable
Claude 3 Opus: 38.2 (#202), GPT-5.4 Pro: —
| Benchmark | Claude 3 Opus | GPT-5.4 Pro |
|---|---|---|
| LMArena Longer Query | 1259 | — |
Writing & Preference Not comparable
Claude 3 Opus: 47.2 (#213), GPT-5.4 Pro: —
| Benchmark | Claude 3 Opus | GPT-5.4 Pro |
|---|---|---|
| LMArena Text | 1262 | — |
| LMArena Creative Writing | 1235 | — |
| LMArena Multi-Turn | 1275 | — |
| LiveBench Language | 50.4% | — |
Frequently asked questions
Is Claude 3 Opus better than GPT-5.4 Pro?
GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 29.5 on the Noometry Index.
Is Claude 3 Opus or GPT-5.4 Pro better for coding?
GPT-5.4 Pro scores higher on coding benchmarks: 43.2 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3 Opus and GPT-5.4 Pro share?
7 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and GPT-5.4 Pro has 16.