Model comparison
GPT-5 Nano vs o1-mini
GPT-5 Nano and o1-mini score almost the same on the Noometry Index (33.4 vs 33.7), so choose on price, context window or the category you care about most.
Last verified . 23 shared benchmarks.
Summary
- They share 23 benchmarks with published results for both. GPT-5 Nano scores higher in 5 categories and o1-mini in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where o1-mini leads 48.6 to 39.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 81.1% for GPT-5 Nano and 46.9% for o1-mini.
Side by side
| GPT-5 Nano | o1-mini | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 33.4 | 33.7 |
| Released | 2025-08-07 | 2024-09-12 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.40 | — |
| Results tracked | 48 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1-mini leads
GPT-5 Nano: 33.3 (#248), o1-mini: 35.1 (#218)
| Benchmark | GPT-5 Nano | o1-mini |
|---|---|---|
| WeirdML | 38.1% | 36.3% |
| LMArena Coding | 1351 | 1362 |
| SWE-bench Verified (bash only) | 34.8% | — |
| Aider Polyglot | — | 32.9% |
| LiveBench Coding | — | 48% |
| ALE-Bench | 718.67 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 78.8% |
Agentic & Tool Use GPT-5 Nano leads
GPT-5 Nano: 25.6 (#99), o1-mini: 24.3 (#112)
| Benchmark | GPT-5 Nano | o1-mini |
|---|---|---|
| Terminal-Bench | 21.8% | — |
| Berkeley Function Calling Leaderboard | 51.5% | — |
| Cybench | — | 10% |
Reasoning GPT-5 Nano leads
GPT-5 Nano: 16.4 (#291), o1-mini: 8.9 (#340)
| Benchmark | GPT-5 Nano | o1-mini |
|---|---|---|
| ARC-AGI-2 | 2.6% | 0.8% |
| ARC-AGI-1 | 20.7% | 14% |
| LMArena Hard Prompts | 1329 | 1333 |
| Epoch Capabilities Index | 139.39 | 135.82 |
| SimpleBench | — | 18.1% |
| Kagi LLM Benchmark | 62.2% | — |
| Chess Puzzles | 27% | — |
| LiveBench Reasoning | — | 72.3% |
| Mystery Game Puzzles | 9% | — |
| DTBench | 62.7% | — |
| LiveBench Data Analysis | — | 57.9% |
| LMCA | 7.9% | — |
| ForecastBench | 59.1 | — |
| LiveBench | — | 57.8% |
Math o1-mini leads
GPT-5 Nano: 29.1 (#221), o1-mini: 33.7 (#168)
| Benchmark | GPT-5 Nano | o1-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 81.1% | 46.9% |
| LMArena Math | 1318 | 1358 |
| MATH Level 5 | 95.2% | 89.2% |
| FrontierMath (Feb 2025 set) | 8.3% | 1.7% |
| FrontierMath (Tiers 1-3) | 20% | — |
| FrontierMath Tier 4 | 2.4% | — |
| ProofBench | 12% | — |
| Omni-MATH | 54.6% | — |
| LiveBench Math | — | 62% |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Too close to call
GPT-5 Nano: 35.8 (#166), o1-mini: 34.8 (#180)
| Benchmark | GPT-5 Nano | o1-mini |
|---|---|---|
| GPQA Diamond | 69.4% | 62.4% |
| LMArena Expert | 1321 | 1316 |
| SimpleQA Verified | 11.7% | — |
| MMLU-Pro | 77.8% | — |
| Confabulations | — | 18.6% |
| Vectara Hallucination Rate | 10.5% | — |
| GPQA (HELM) | 67.9% | — |
Multimodal Not comparable
GPT-5 Nano: 30.7 (#102), o1-mini: —
| Benchmark | GPT-5 Nano | o1-mini |
|---|---|---|
| LMArena Vision | 1159 | — |
| VPCT | 37.2% | — |
Multilingual GPT-5 Nano leads
GPT-5 Nano: 45.5 (#167), o1-mini: 43.8 (#177)
| Benchmark | GPT-5 Nano | o1-mini |
|---|---|---|
| LMArena Non-English | 1313 | 1289 |
| LMArena Chinese | 1355 | 1314 |
| LMArena German | 1329 | 1278 |
| LMArena Korean | 1269 | 1223 |
| LMArena Russian | 1296 | 1283 |
| LMArena Spanish | 1360 | 1302 |
| LMArena French | — | 1292 |
| LMArena Japanese | — | 1245 |
Instruction Following GPT-5 Nano leads
GPT-5 Nano: 75.2 (#72), o1-mini: 67.0 (#200)
| Benchmark | GPT-5 Nano | o1-mini |
|---|---|---|
| LMArena Instruction Following | 1306 | 1304 |
| LiveBench Instruction Following | — | 65.4% |
| IFEval | 93.2% | — |
Long Context o1-mini leads
GPT-5 Nano: 31.3 (#275), o1-mini: 40.1 (#156)
| Benchmark | GPT-5 Nano | o1-mini |
|---|---|---|
| LMArena Longer Query | 1313 | 1321 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference o1-mini leads
GPT-5 Nano: 39.4 (#244), o1-mini: 48.6 (#196)
| Benchmark | GPT-5 Nano | o1-mini |
|---|---|---|
| LMArena Text | 1320 | 1317 |
| LMArena Creative Writing | 1250 | 1244 |
| LMArena Multi-Turn | 1311 | 1314 |
| Short-Story Creative Writing | — | 64.9% |
| EQ-Bench Creative Writing | 705 | — |
| WildBench | 80.6% | — |
| LiveBench Language | — | 40.9% |
Frequently asked questions
Is GPT-5 Nano better than o1-mini?
GPT-5 Nano and o1-mini score almost the same on the Noometry Index (33.4 vs 33.7), so choose on price, context window or the category you care about most.
Is GPT-5 Nano or o1-mini better for coding?
o1-mini scores higher on coding benchmarks: 35.1 versus 33.3 in the Noometry coding category.
How many benchmarks do GPT-5 Nano and o1-mini share?
23 benchmarks have published results for both models. GPT-5 Nano has 48 scored results on Noometry and o1-mini has 39.