Model comparison
Claude Opus 4 vs GPT-4o mini
Claude Opus 4 is the stronger model overall, scoring 43.1 to 25.5 on the Noometry Index. GPT-4o mini costs 114× less per token, which makes it the better buy when Claude Opus 4's lead doesn't matter for your workload.
Last verified . 39 shared benchmarks.
Summary
- They share 39 benchmarks with published results for both. Claude Opus 4 scores higher in 10 categories and GPT-4o mini in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Opus 4 leads 42.0 to 10.4.
- The biggest single-benchmark swing is Aider Polyglot: 72% for Claude Opus 4 and 3.6% for GPT-4o mini.
- GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $15 / $75 for Claude Opus 4.
- Claude Opus 4 accepts more context: 200K tokens versus 128K.
Side by side
| Claude Opus 4 | GPT-4o mini | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 43.1 | 25.5 |
| Released | 2025-05-22 | 2024-07-18 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 128K |
| Max output | 32K | 16K |
| Input $ / M tokens | $15 | $0.15 |
| Output $ / M tokens | $75 | $0.60 |
| Results tracked | 56 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4 leads
Claude Opus 4: 47.2 (#62), GPT-4o mini: 22.0 (#335)
| Benchmark | Claude Opus 4 | GPT-4o mini |
|---|---|---|
| Aider Polyglot | 72% | 3.6% |
| WeirdML | 43.7% | 11.8% |
| LMArena Coding | 1442 | 1290 |
| SWE-bench Verified | 70.7% | — |
| SWE-bench Verified (bash only) | 67.6% | — |
| GSO | 6.9% | — |
| BigCodeBench Instruct | — | 46.1% |
| LiveBench Coding | — | 43.1% |
| BigCodeBench Complete | — | 57.4% |
| AlgoTune | 1.33 | — |
| HumanEval+ | — | 83.5% |
| MBPP+ | — | 72.2% |
Agentic & Tool Use Claude Opus 4 leads
Claude Opus 4: 34.8 (#42), GPT-4o mini: 27.5 (#101)
| Benchmark | Claude Opus 4 | GPT-4o mini |
|---|---|---|
| Cybench | 38% | — |
| DeepResearch Bench | 46.8% | — |
| BALROG | — | 17.4% |
| LMArena Search | 1127 | — |
| METR Time Horizons | 63.9% | — |
Reasoning Claude Opus 4 leads
Claude Opus 4: 27.3 (#121), GPT-4o mini: 8.7 (#347)
| Benchmark | Claude Opus 4 | GPT-4o mini |
|---|---|---|
| ARC-AGI-2 | 8.6% | 0% |
| SimpleBench | 58.8% | 10.7% |
| Kagi LLM Benchmark | 74.3% | 28.8% |
| LMArena Hard Prompts | 1399 | 1267 |
| DTBench | 81.6% | 54.4% |
| LMCA | 37.4% | 10.4% |
| Epoch Capabilities Index | 142.67 | 126.56 |
| ARC-AGI-1 | 35.7% | — |
| CritPt | 0.3% | — |
| Chess Puzzles | — | 0% |
| EnigmaEval | 5.6% | — |
| LiveBench Reasoning | — | 32.8% |
| Mystery Game Puzzles | — | 12% |
| LiveBench Data Analysis | — | 50% |
| ForecastBench | 61.1 | — |
| LiveBench | — | 41.3% |
| PIQA | — | 88.7% |
Math Claude Opus 4 leads
Claude Opus 4: 42.0 (#86), GPT-4o mini: 10.4 (#314)
| Benchmark | Claude Opus 4 | GPT-4o mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 64.4% | 6.9% |
| Omni-MATH | 61.6% | 28% |
| LMArena Math | 1390 | 1267 |
| MATH Level 5 | 85% | 52.6% |
| FrontierMath (Tiers 1-3) | — | 0.7% |
| LiveBench Math | — | 36.3% |
| FrontierMath (Feb 2025 set) | 4.5% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
| GSM8K | — | 91.3% |
Knowledge Claude Opus 4 leads
Claude Opus 4: 44.0 (#88), GPT-4o mini: 17.7 (#284)
| Benchmark | Claude Opus 4 | GPT-4o mini |
|---|---|---|
| GPQA Diamond | 76.3% | 37.7% |
| MMLU-Pro | 87.5% | 60.3% |
| Confabulations | 15.9% | 37.2% |
| GPQA (HELM) | 70.8% | 36.8% |
| LMArena Expert | 1386 | 1235 |
| Humanity's Last Exam | 10.7% | — |
| SimpleQA Verified | — | 8.3% |
| Vectara Hallucination Rate | 12% | — |
| BoolQ | — | 88.7% |
| MMLU | — | 81.8% |
Multimodal Claude Opus 4 leads
Claude Opus 4: 31.5 (#106), GPT-4o mini: 25.9 (#122)
| Benchmark | Claude Opus 4 | GPT-4o mini |
|---|---|---|
| LMArena Vision | 1192 | 1066 |
| GeoBench | 49% | 64% |
| VPCT | 38% | 34% |
| Video-MME | — | 64.8% |
Multilingual Claude Opus 4 leads
Claude Opus 4: 48.8 (#138), GPT-4o mini: 42.0 (#199)
| Benchmark | Claude Opus 4 | GPT-4o mini |
|---|---|---|
| LMArena Non-English | 1362 | 1266 |
| LMArena Chinese | 1386 | 1265 |
| LMArena French | 1372 | 1297 |
| LMArena German | 1391 | 1272 |
| LMArena Japanese | 1331 | 1216 |
| LMArena Korean | 1321 | 1195 |
| LMArena Russian | 1392 | 1275 |
| LMArena Spanish | 1389 | 1276 |
Instruction Following Claude Opus 4 leads
Claude Opus 4: 77.1 (#28), GPT-4o mini: 61.9 (#239)
| Benchmark | Claude Opus 4 | GPT-4o mini |
|---|---|---|
| IFEval | 91.8% | 78.2% |
| LMArena Instruction Following | 1406 | 1258 |
| LiveBench Instruction Following | — | 56.8% |
Long Context Too close to call
Claude Opus 4: 39.6 (#172), GPT-4o mini: 39.1 (#186)
| Benchmark | Claude Opus 4 | GPT-4o mini |
|---|---|---|
| LMArena Longer Query | 1422 | 1289 |
| Fiction.LiveBench | 61.1% | — |
Writing & Preference Claude Opus 4 leads
Claude Opus 4: 61.2 (#89), GPT-4o mini: 39.5 (#248)
| Benchmark | Claude Opus 4 | GPT-4o mini |
|---|---|---|
| LMArena Text | 1377 | 1286 |
| LMArena Creative Writing | 1387 | 1268 |
| Short-Story Creative Writing | 83.6% | 67.2% |
| EQ-Bench Creative Writing | 1580 | 873 |
| WildBench | 85.2% | 79.1% |
| LMArena Multi-Turn | 1396 | 1285 |
| LiveBench Language | — | 28.6% |
Frequently asked questions
Is Claude Opus 4 better than GPT-4o mini?
Claude Opus 4 is the stronger model overall, scoring 43.1 to 25.5 on the Noometry Index. GPT-4o mini costs 114× less per token, which makes it the better buy when Claude Opus 4's lead doesn't matter for your workload.
Which is cheaper, Claude Opus 4 or GPT-4o mini?
GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Claude Opus 4 lists at $15 and $75.
Is Claude Opus 4 or GPT-4o mini better for coding?
Claude Opus 4 scores higher on coding benchmarks: 47.2 versus 22.0 in the Noometry coding category.
Which has the bigger context window?
Claude Opus 4 does, with 200K tokens against 128K.
How many benchmarks do Claude Opus 4 and GPT-4o mini share?
39 benchmarks have published results for both models. Claude Opus 4 has 56 scored results on Noometry and GPT-4o mini has 60.