Model comparison
GPT-5 Mini vs o1-mini
GPT-5 Mini is the stronger model overall, scoring 41.8 to 34.0 on the Noometry Index.
Last verified . 27 shared benchmarks.
Summary
- They share 27 benchmarks with published results for both. GPT-5 Mini scores higher in 9 categories and o1-mini in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5 Mini leads 23.9 to 8.8.
- The biggest single-benchmark swing is ARC-AGI-1: 54.3% for GPT-5 Mini and 14% for o1-mini.
Side by side
| GPT-5 Mini | o1-mini | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 41.8 | 34.0 |
| Released | 2025-08-07 | 2024-09-12 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $2 | — |
| Results tracked | 60 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 Mini leads
GPT-5 Mini: 40.1 (#146), o1-mini: 35.5 (#224)
| Benchmark | GPT-5 Mini | o1-mini |
|---|---|---|
| WeirdML | 52.7% | 36.3% |
| LMArena Coding | 1406 | 1362 |
| SWE-bench Verified | 64.7% | — |
| SWE-bench Verified (bash only) | 59.8% | — |
| Aider Polyglot | — | 32.9% |
| SWE-bench Multilingual | 39.7% | — |
| SciCode | 39.2% | — |
| LiveBench Coding | — | 48% |
| ALE-Bench | 799.77 | — |
| AlgoTune | 1.38 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 78.8% |
Agentic & Tool Use GPT-5 Mini leads
GPT-5 Mini: 31.1 (#70), o1-mini: 24.6 (#118)
| Benchmark | GPT-5 Mini | o1-mini |
|---|---|---|
| Terminal-Bench | 34.8% | — |
| Berkeley Function Calling Leaderboard | 55.5% | — |
| Cybench | — | 10% |
| Vending-Bench 2 | -31.18 | — |
Reasoning GPT-5 Mini leads
GPT-5 Mini: 23.9 (#168), o1-mini: 8.8 (#346)
| Benchmark | GPT-5 Mini | o1-mini |
|---|---|---|
| ARC-AGI-2 | 4.4% | 0.8% |
| ARC-AGI-1 | 54.3% | 14% |
| LMArena Hard Prompts | 1380 | 1333 |
| Epoch Capabilities Index | 145.52 | 135.82 |
| SimpleBench | — | 18.1% |
| Kagi LLM Benchmark | 70.3% | — |
| CritPt | 0% | — |
| Chess Puzzles | 30% | — |
| EnigmaEval | 8.2% | — |
| LiveBench Reasoning | — | 72.3% |
| Mystery Game Puzzles | 10% | — |
| DTBench | 80.5% | — |
| LiveBench Data Analysis | — | 57.9% |
| LMCA | 34.2% | — |
| ForecastBench | 61 | — |
| LiveBench | — | 57.8% |
Math GPT-5 Mini leads
GPT-5 Mini: 46.7 (#69), o1-mini: 35.4 (#186)
| Benchmark | GPT-5 Mini | o1-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 86.7% | 46.9% |
| LMArena Math | 1378 | 1358 |
| MATH Level 5 | 97.8% | 89.2% |
| FrontierMath (Feb 2025 set) | 27.2% | 1.7% |
| FrontierMath (Tiers 1-3) | 46.7% | — |
| FrontierMath Tier 4 | 12.2% | — |
| ProofBench | 9% | — |
| Omni-MATH | 72.2% | — |
| LiveBench Math | — | 62% |
| FrontierMath Tier 4 (v1) | 6.3% | — |
Knowledge GPT-5 Mini leads
GPT-5 Mini: 45.6 (#86), o1-mini: 34.9 (#192)
| Benchmark | GPT-5 Mini | o1-mini |
|---|---|---|
| GPQA Diamond | 75% | 62.4% |
| Confabulations | 13.3% | 18.6% |
| LMArena Expert | 1379 | 1316 |
| Humanity's Last Exam | 19.4% | — |
| SimpleQA Verified | 21.6% | — |
| MMLU-Pro | 83.5% | — |
| Vectara Hallucination Rate | 12.9% | — |
| GPQA (HELM) | 75.6% | — |
Multimodal Not comparable
GPT-5 Mini: 35.6 (#85), o1-mini: —
| Benchmark | GPT-5 Mini | o1-mini |
|---|---|---|
| LMArena Vision | 1202 | — |
| VPCT | 40.2% | — |
Multilingual GPT-5 Mini leads
GPT-5 Mini: 48.9 (#137), o1-mini: 43.6 (#182)
| Benchmark | GPT-5 Mini | o1-mini |
|---|---|---|
| LMArena Non-English | 1363 | 1289 |
| LMArena Chinese | 1385 | 1314 |
| LMArena French | 1386 | 1293 |
| LMArena German | 1366 | 1278 |
| LMArena Japanese | 1341 | 1245 |
| LMArena Korean | 1308 | 1223 |
| LMArena Russian | 1362 | 1283 |
| LMArena Spanish | 1355 | 1303 |
Instruction Following GPT-5 Mini leads
GPT-5 Mini: 76.2 (#46), o1-mini: 66.7 (#206)
| Benchmark | GPT-5 Mini | o1-mini |
|---|---|---|
| LMArena Instruction Following | 1357 | 1304 |
| LiveBench Instruction Following | — | 65.4% |
| IFEval | 92.7% | — |
Long Context GPT-5 Mini leads
GPT-5 Mini: 41.9 (#132), o1-mini: 40.1 (#161)
| Benchmark | GPT-5 Mini | o1-mini |
|---|---|---|
| LMArena Longer Query | 1355 | 1320 |
| Fiction.LiveBench | 69.4% | — |
Writing & Preference GPT-5 Mini leads
GPT-5 Mini: 55.2 (#148), o1-mini: 48.4 (#202)
| Benchmark | GPT-5 Mini | o1-mini |
|---|---|---|
| LMArena Text | 1373 | 1317 |
| LMArena Creative Writing | 1325 | 1244 |
| Short-Story Creative Writing | 83.1% | 64.9% |
| LMArena Multi-Turn | 1363 | 1314 |
| EQ-Bench Creative Writing | 1313 | — |
| WildBench | 85.5% | — |
| LiveBench Language | — | 40.9% |
Frequently asked questions
Is GPT-5 Mini better than o1-mini?
GPT-5 Mini is the stronger model overall, scoring 41.8 to 34.0 on the Noometry Index.
Is GPT-5 Mini or o1-mini better for coding?
GPT-5 Mini scores higher on coding benchmarks: 40.1 versus 35.5 in the Noometry coding category.
How many benchmarks do GPT-5 Mini and o1-mini share?
27 benchmarks have published results for both models. GPT-5 Mini has 60 scored results on Noometry and o1-mini has 39.