Model comparison
GPT-5 Nano vs Ministral 8B
GPT-5 Nano is the stronger model overall, scoring 33.5 to 28.2 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AISummary
- They share 17 benchmarks with published results for both. GPT-5 Nano scores higher in 5 categories and Ministral 8B in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5 Nano leads 35.9 to 12.6.
- The biggest single-benchmark swing is MATH Level 5: 95.2% for GPT-5 Nano and 14.9% for Ministral 8B.
- GPT-5 Nano is cheaper at $0.05 / $0.40 per million input/output tokens, against $0.15 / $0.15 for Ministral 8B.
- GPT-5 Nano accepts more context: 400K tokens versus 262K.
- Ministral 8B has downloadable open weights; the other is API-only.
Side by side
| GPT-5 Nano | Ministral 8B | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 33.5 | 28.2 |
| Released | 2025-08-07 | 2024-10-01 |
| Weights | Proprietary | Open |
| Context window | 400K | 262K |
| Max output | 128K | 262K |
| Input $ / M tokens | $0.05 | $0.15 |
| Output $ / M tokens | $0.40 | $0.15 |
| Results tracked | 49 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Ministral 8B leads
GPT-5 Nano: 33.6 (#254), Ministral 8B: 35.0 (#230)
| Benchmark | GPT-5 Nano | Ministral 8B |
|---|---|---|
| LMArena Coding | 1351 | 1202 |
| SWE-bench Verified (bash only) | 34.8% | — |
| WeirdML | 38.1% | — |
| ALE-Bench | 718.67 | — |
Agentic & Tool Use GPT-5 Nano leads
GPT-5 Nano: 25.8 (#106), Ministral 8B: 16.4 (#148)
| Benchmark | GPT-5 Nano | Ministral 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 51.5% | 11.1% |
| Terminal-Bench | 21.8% | — |
Reasoning Ministral 8B leads
GPT-5 Nano: 16.3 (#306), Ministral 8B: 18.4 (#281)
| Benchmark | GPT-5 Nano | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | 1328 | 1191 |
| DTBench | 62.7% | 45.7% |
| ARC-AGI-2 | 2.6% | — |
| Kagi LLM Benchmark | 62.2% | — |
| ARC-AGI-1 | 20.7% | — |
| Chess Puzzles | 27% | — |
| Mystery Game Puzzles | 9% | — |
| LMCA | 7.9% | — |
| Epoch Capabilities Index | 139.38 | — |
| ForecastBench | 59.1 | — |
Math GPT-5 Nano leads
GPT-5 Nano: 29.4 (#241), Ministral 8B: 25.7 (#267)
| Benchmark | GPT-5 Nano | Ministral 8B |
|---|---|---|
| LMArena Math | 1317 | 1188 |
| MATH Level 5 | 95.2% | 14.9% |
| FrontierMath (Tiers 1-3) | 20% | — |
| FrontierMath Tier 4 | 2.4% | — |
| OTIS Mock AIME 2024-2025 | 81.1% | — |
| ProofBench | 12% | — |
| Omni-MATH | 54.6% | — |
| FrontierMath (Feb 2025 set) | 8.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GPT-5 Nano leads
GPT-5 Nano: 35.9 (#178), Ministral 8B: 12.6 (#297)
| Benchmark | GPT-5 Nano | Ministral 8B |
|---|---|---|
| GPQA Diamond | 69.4% | 27.1% |
| Vectara Hallucination Rate | 10.5% | 7.4% |
| LMArena Expert | 1321 | 1170 |
| SimpleQA Verified | 11.7% | — |
| MMLU-Pro | 77.8% | — |
| GPQA (HELM) | 67.9% | — |
Multimodal Not comparable
GPT-5 Nano: 31.3 (#108), Ministral 8B: —
| Benchmark | GPT-5 Nano | Ministral 8B |
|---|---|---|
| LMArena Vision | 1159 | — |
| VPCT | 37.2% | — |
Multilingual GPT-5 Nano leads
GPT-5 Nano: 45.3 (#172), Ministral 8B: 35.1 (#247)
| Benchmark | GPT-5 Nano | Ministral 8B |
|---|---|---|
| LMArena Non-English | 1313 | 1165 |
| LMArena Chinese | 1356 | 1193 |
| LMArena Russian | 1296 | 1195 |
| LMArena German | 1327 | — |
| LMArena Japanese | 1226 | — |
| LMArena Korean | 1269 | — |
| LMArena Spanish | 1360 | — |
Instruction Following GPT-5 Nano leads
GPT-5 Nano: 75.0 (#79), Ministral 8B: 60.5 (#250)
| Benchmark | GPT-5 Nano | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | 1306 | 1161 |
| IFEval | 93.2% | — |
Long Context Ministral 8B leads
GPT-5 Nano: 31.3 (#281), Ministral 8B: 36.7 (#227)
| Benchmark | GPT-5 Nano | Ministral 8B |
|---|---|---|
| LMArena Longer Query | 1312 | 1212 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference Too close to call
GPT-5 Nano: 39.1 (#249), Ministral 8B: 39.6 (#246)
| Benchmark | GPT-5 Nano | Ministral 8B |
|---|---|---|
| LMArena Text | 1320 | 1191 |
| LMArena Creative Writing | 1249 | 1175 |
| LMArena Multi-Turn | 1311 | 1166 |
| EQ-Bench Creative Writing | 705 | — |
| WildBench | 80.6% | — |
Frequently asked questions
Is GPT-5 Nano better than Ministral 8B?
GPT-5 Nano is the stronger model overall, scoring 33.5 to 28.2 on the Noometry Index.
Which is cheaper, GPT-5 Nano or Ministral 8B?
GPT-5 Nano is cheaper. It lists at $0.05 per million input tokens and $0.40 per million output tokens; Ministral 8B lists at $0.15 and $0.15.
Is GPT-5 Nano or Ministral 8B better for coding?
Ministral 8B scores higher on coding benchmarks: 35.0 versus 33.6 in the Noometry coding category.
Which has the bigger context window?
GPT-5 Nano does, with 400K tokens against 262K.
How many benchmarks do GPT-5 Nano and Ministral 8B share?
17 benchmarks have published results for both models. GPT-5 Nano has 49 scored results on Noometry and Ministral 8B has 17.