Model comparison
GPT-5.2 vs Ministral 8B
GPT-5.2 is the stronger model overall, scoring 54.1 to 27.8 on the Noometry Index. Ministral 8B costs 48× less per token, which makes it the better buy when GPT-5.2's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
Mistral AISummary
- They share 16 benchmarks with published results for both. GPT-5.2 scores higher in 9 categories and Ministral 8B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.2 leads 59.2 to 12.5.
- The biggest single-benchmark swing is GPQA Diamond: 91.4% for GPT-5.2 and 27.1% for Ministral 8B.
- Ministral 8B is cheaper at $0.10 / $0.10 per million input/output tokens, against $1.75 / $14 for GPT-5.2.
- GPT-5.2 accepts more context: 400K tokens versus 128K.
- Ministral 8B has downloadable open weights; the other is API-only.
Side by side
| GPT-5.2 | Ministral 8B | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 54.1 | 27.8 |
| Released | 2025-12-11 | 2024-10-01 |
| Weights | Proprietary | Open |
| Context window | 400K | 128K |
| Max output | 128K | 128K |
| Input $ / M tokens | $1.75 | $0.10 |
| Output $ / M tokens | $14 | $0.10 |
| Results tracked | 67 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.2 leads
GPT-5.2: 52.2 (#32), Ministral 8B: 34.4 (#226)
| Benchmark | GPT-5.2 | Ministral 8B |
|---|---|---|
| LMArena Coding | 1447 | 1202 |
| SWE-bench Verified | 73.8% | — |
| SWE-bench Verified (bash only) | 72.8% | — |
| LMArena WebDev | 1415 | — |
| SWE-bench Multilingual | 66.7% | — |
| GSO | 27.4% | — |
| WeirdML | 72.2% | — |
| ALE-Bench | 1,294 | — |
| AlgoTune | 2.05 | — |
Agentic & Tool Use GPT-5.2 leads
GPT-5.2: 40.0 (#24), Ministral 8B: 16.2 (#140)
| Benchmark | GPT-5.2 | Ministral 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 55.9% | 11.1% |
| Terminal-Bench | 64.9% | — |
| GDPval | 49.7% | — |
| Remote Labor Index | 2.5% | — |
| τ²-bench Airline | 83% | — |
| τ²-bench Banking | 32.2% | — |
| τ²-bench Retail | 81.6% | — |
| τ²-bench Telecom | 89.7% | — |
| DeepResearch Bench | 41.1% | — |
| LMArena Search | 1207 | — |
| METR Time Horizons | 75.3% | — |
| Vending-Bench 2 | 3,591 | — |
Reasoning GPT-5.2 leads
GPT-5.2: 50.1 (#33), Ministral 8B: 17.7 (#279)
| Benchmark | GPT-5.2 | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | 1445 | 1191 |
| DTBench | 90.9% | 45.7% |
| ARC-AGI-2 | 52.9% | — |
| SimpleBench | 45.8% | — |
| Kagi LLM Benchmark | 73.3% | — |
| NYT Connections (extended) | 83.6% | — |
| ARC-AGI-1 | 86.2% | — |
| Chess Puzzles | 49% | — |
| EnigmaEval | 10.4% | — |
| EBR-Bench | 23% | — |
| Mystery Game Puzzles | 23% | — |
| LMCA | 43.9% | — |
| Epoch Capabilities Index | 153.45 | — |
| ForecastBench | 60.1 | — |
Math GPT-5.2 leads
GPT-5.2: 59.8 (#32), Ministral 8B: 23.7 (#262)
| Benchmark | GPT-5.2 | Ministral 8B |
|---|---|---|
| LMArena Math | 1439 | 1188 |
| FrontierMath (Tiers 1-3) | 67.4% | — |
| FrontierMath Tier 4 | 31.7% | — |
| MathArena Final-Answer Competitions | 72% | — |
| OTIS Mock AIME 2024-2025 | 96.1% | — |
| ProofBench | 15% | — |
| MATH Level 5 | — | 14.9% |
| FrontierMath (Feb 2025 set) | 40.7% | — |
| FrontierMath Tier 4 (v1) | 18.8% | — |
Knowledge GPT-5.2 leads
GPT-5.2: 59.2 (#29), Ministral 8B: 12.5 (#292)
| Benchmark | GPT-5.2 | Ministral 8B |
|---|---|---|
| GPQA Diamond | 91.4% | 27.1% |
| Vectara Hallucination Rate | 8.4% | 7.4% |
| LMArena Expert | 1445 | 1170 |
| Humanity's Last Exam | 27.8% | — |
| SimpleQA Verified | 37.1% | — |
Multimodal Not comparable
GPT-5.2: 50.9 (#7), Ministral 8B: —
| Benchmark | GPT-5.2 | Ministral 8B |
|---|---|---|
| LMArena Vision | 1268 | — |
| VPCT | 84% | — |
| Furniture Assembly | 38.3% | — |
| LMArena Document | 1405 | — |
Multilingual GPT-5.2 leads
GPT-5.2: 53.6 (#63), Ministral 8B: 35.3 (#242)
| Benchmark | GPT-5.2 | Ministral 8B |
|---|---|---|
| LMArena Non-English | 1425 | 1165 |
| LMArena Chinese | 1460 | 1193 |
| LMArena Russian | 1440 | 1195 |
| LMArena French | 1456 | — |
| LMArena German | 1448 | — |
| LMArena Japanese | 1421 | — |
| LMArena Korean | 1390 | — |
| LMArena Spanish | 1433 | — |
Instruction Following GPT-5.2 leads
GPT-5.2: 74.9 (#83), Ministral 8B: 60.7 (#245)
| Benchmark | GPT-5.2 | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | 1417 | 1161 |
Long Context GPT-5.2 leads
GPT-5.2: 44.0 (#74), Ministral 8B: 36.7 (#222)
| Benchmark | GPT-5.2 | Ministral 8B |
|---|---|---|
| LMArena Longer Query | 1428 | 1212 |
| CL-bench | 18.2% | — |
Writing & Preference GPT-5.2 leads
GPT-5.2: 67.0 (#30), Ministral 8B: 39.8 (#241)
| Benchmark | GPT-5.2 | Ministral 8B |
|---|---|---|
| LMArena Text | 1439 | 1191 |
| LMArena Creative Writing | 1402 | 1175 |
| LMArena Multi-Turn | 1458 | 1166 |
| EQ-Bench Creative Writing | 1703 | — |
Frequently asked questions
Is GPT-5.2 better than Ministral 8B?
GPT-5.2 is the stronger model overall, scoring 54.1 to 27.8 on the Noometry Index. Ministral 8B costs 48× less per token, which makes it the better buy when GPT-5.2's lead doesn't matter for your workload.
Which is cheaper, GPT-5.2 or Ministral 8B?
Ministral 8B is cheaper. It lists at $0.10 per million input tokens and $0.10 per million output tokens; GPT-5.2 lists at $1.75 and $14.
Is GPT-5.2 or Ministral 8B better for coding?
GPT-5.2 scores higher on coding benchmarks: 52.2 versus 34.4 in the Noometry coding category.
Which has the bigger context window?
GPT-5.2 does, with 400K tokens against 128K.
How many benchmarks do GPT-5.2 and Ministral 8B share?
16 benchmarks have published results for both models. GPT-5.2 has 67 scored results on Noometry and Ministral 8B has 17.