Model comparison
Claude 3 Opus vs o4-mini
o4-mini is the stronger model overall, scoring 41.6 to 29.5 on the Noometry Index.
Last verified . 32 shared benchmarks.
Summary
- They share 32 benchmarks with published results for both. Claude 3 Opus scores higher in 0 categories and o4-mini in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where o4-mini leads 40.8 to 14.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.7% for Claude 3 Opus and 81.7% for o4-mini.
Side by side
| Claude 3 Opus | o4-mini | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 29.5 | 41.6 |
| Released | 2024-02-29 | 2025-04-16 |
| Weights | Proprietary | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $1.10 |
| Output $ / M tokens | — | $4.40 |
| Results tracked | 46 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o4-mini leads
Claude 3 Opus: 32.9 (#267), o4-mini: 40.9 (#127)
| Benchmark | Claude 3 Opus | o4-mini |
|---|---|---|
| WeirdML | 19.2% | 52.6% |
| LMArena Coding | 1264 | 1368 |
| SWE-bench Verified (bash only) | — | 45% |
| Aider Polyglot | — | 72% |
| GSO | — | 3.6% |
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 38.6% | — |
| BigCodeBench Complete | 57.4% | — |
| CadEval | — | 62% |
| ALE-Bench | — | 826.17 |
| AlgoTune | — | 1.72 |
| HumanEval+ | 77.4% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use o4-mini leads
Claude 3 Opus: 24.6 (#116), o4-mini: 32.6 (#61)
| Benchmark | Claude 3 Opus | o4-mini |
|---|---|---|
| METR Time Horizons | 29.5% | 63.9% |
| Berkeley Function Calling Leaderboard | — | 53.2% |
| GDPval | — | 25.3% |
| Cybench | 10% | — |
Reasoning o4-mini leads
Claude 3 Opus: 14.6 (#324), o4-mini: 24.6 (#162)
| Benchmark | Claude 3 Opus | o4-mini |
|---|---|---|
| SimpleBench | 23.5% | 38.7% |
| Chess Puzzles | 5% | 26% |
| EnigmaEval | 0.8% | 9.2% |
| LMArena Hard Prompts | 1245 | 1351 |
| DTBench | 61.6% | 77.6% |
| LMCA | 17% | 26.5% |
| Epoch Capabilities Index | 126.91 | 145.64 |
| ForecastBench | 58.4 | 61.8 |
| ARC-AGI-2 | — | 6.1% |
| Kagi LLM Benchmark | — | 67.6% |
| ARC-AGI-1 | — | 58.7% |
| CritPt | — | 0.6% |
| LiveBench Reasoning | 40.6% | — |
| Mystery Game Puzzles | — | 5% |
| LiveBench Data Analysis | 57.9% | — |
| LiveBench | 49.2% | — |
| WinoGrande | 88.5% | — |
Math o4-mini leads
Claude 3 Opus: 14.8 (#299), o4-mini: 40.8 (#89)
| Benchmark | Claude 3 Opus | o4-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.7% | 81.7% |
| LMArena Math | 1273 | 1389 |
| MATH Level 5 | 37.5% | 97.8% |
| FrontierMath (Tiers 1-3) | — | 36.1% |
| FrontierMath Tier 4 | — | 4.9% |
| Omni-MATH | — | 72% |
| LiveBench Math | 43.6% | — |
| FrontierMath (Feb 2025 set) | — | 24.8% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge o4-mini leads
Claude 3 Opus: 24.5 (#267), o4-mini: 43.6 (#91)
| Benchmark | Claude 3 Opus | o4-mini |
|---|---|---|
| GPQA Diamond | 47.2% | 79.6% |
| SimpleQA Verified | 12.6% | 19.6% |
| Confabulations | 22.7% | 15.8% |
| LMArena Expert | 1223 | 1343 |
| Humanity's Last Exam | — | 18.1% |
| MMLU-Pro | — | 82% |
| Vectara Hallucination Rate | — | 18.6% |
| GPQA (HELM) | — | 73.5% |
| MMLU | 84.6% | — |
Multimodal o4-mini leads
Claude 3 Opus: 27.1 (#116), o4-mini: 40.2 (#49)
| Benchmark | Claude 3 Opus | o4-mini |
|---|---|---|
| LMArena Vision | 1023 | 1194 |
| GeoBench | — | 64% |
| VPCT | — | 57.5% |
Multilingual o4-mini leads
Claude 3 Opus: 41.4 (#207), o4-mini: 47.0 (#154)
| Benchmark | Claude 3 Opus | o4-mini |
|---|---|---|
| LMArena Non-English | 1258 | 1337 |
| LMArena Chinese | 1248 | 1354 |
| LMArena French | 1275 | 1364 |
| LMArena German | 1258 | 1336 |
| LMArena Japanese | 1204 | 1308 |
| LMArena Korean | 1187 | 1312 |
| LMArena Russian | 1280 | 1334 |
| LMArena Spanish | 1246 | 1347 |
Instruction Following o4-mini leads
Claude 3 Opus: 64.1 (#228), o4-mini: 75.2 (#68)
| Benchmark | Claude 3 Opus | o4-mini |
|---|---|---|
| LMArena Instruction Following | 1248 | 1321 |
| LiveBench Instruction Following | 63.9% | — |
| IFEval | — | 92.8% |
Long Context o4-mini leads
Claude 3 Opus: 38.2 (#202), o4-mini: 45.5 (#33)
| Benchmark | Claude 3 Opus | o4-mini |
|---|---|---|
| LMArena Longer Query | 1259 | 1315 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference o4-mini leads
Claude 3 Opus: 47.2 (#213), o4-mini: 54.0 (#152)
| Benchmark | Claude 3 Opus | o4-mini |
|---|---|---|
| LMArena Text | 1262 | 1353 |
| LMArena Creative Writing | 1235 | 1294 |
| LMArena Multi-Turn | 1275 | 1350 |
| Short-Story Creative Writing | — | 75% |
| WildBench | — | 85.4% |
| LiveBench Language | 50.4% | — |
Frequently asked questions
Is Claude 3 Opus better than o4-mini?
o4-mini is the stronger model overall, scoring 41.6 to 29.5 on the Noometry Index.
Is Claude 3 Opus or o4-mini better for coding?
o4-mini scores higher on coding benchmarks: 40.9 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3 Opus and o4-mini share?
32 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and o4-mini has 60.