Model comparison
GPT-5.2 vs Mistral Small
GPT-5.2 is the stronger model overall, scoring 54.1 to 33.1 on the Noometry Index. Mistral Small costs 18× less per token, which makes it the better buy when GPT-5.2's lead doesn't matter for your workload.
Last verified . 26 shared benchmarks.
Mistral AISummary
- They share 26 benchmarks with published results for both. GPT-5.2 scores higher in 10 categories and Mistral Small in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.2 leads 59.8 to 15.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 96.1% for GPT-5.2 and 5.8% for Mistral Small.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $1.75 / $14 for GPT-5.2.
- GPT-5.2 accepts more context: 400K tokens versus 256K.
- Mistral Small has downloadable open weights; the other is API-only.
Side by side
| GPT-5.2 | Mistral Small | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 54.1 | 33.1 |
| Released | 2025-12-11 | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | 400K | 256K |
| Max output | 128K | 256K |
| Input $ / M tokens | $1.75 | $0.15 |
| Output $ / M tokens | $14 | $0.60 |
| Results tracked | 67 | 39 |
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), Mistral Small: 33.5 (#242)
| Benchmark | GPT-5.2 | Mistral Small |
|---|---|---|
| LMArena Coding | 1447 | 1363 |
| ALE-Bench | 1,294 | 497.62 |
| SWE-bench Verified | 73.8% | — |
| SWE-bench Verified (bash only) | 72.8% | — |
| LMArena WebDev | 1415 | — |
| SWE-bench Multilingual | 66.7% | — |
| SciCode | — | 26.5% |
| GSO | 27.4% | — |
| WeirdML | 72.2% | — |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |
| AlgoTune | 2.05 | — |
Agentic & Tool Use GPT-5.2 leads
GPT-5.2: 40.0 (#24), Mistral Small: 27.9 (#87)
| Benchmark | GPT-5.2 | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | 55.9% | 37.1% |
| 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), Mistral Small: 19.3 (#238)
| Benchmark | GPT-5.2 | Mistral Small |
|---|---|---|
| Kagi LLM Benchmark | 73.3% | 37.8% |
| LMArena Hard Prompts | 1445 | 1336 |
| DTBench | 90.9% | 70.9% |
| LMCA | 43.9% | 20.6% |
| ARC-AGI-2 | 52.9% | — |
| SimpleBench | 45.8% | — |
| NYT Connections (extended) | 83.6% | — |
| ARC-AGI-1 | 86.2% | — |
| CritPt | — | 0% |
| Chess Puzzles | 49% | — |
| EnigmaEval | 10.4% | — |
| EBR-Bench | 23% | — |
| LiveBench Reasoning | — | 44.8% |
| Mystery Game Puzzles | 23% | — |
| LiveBench Data Analysis | — | 53.7% |
| Epoch Capabilities Index | 153.45 | — |
| ForecastBench | 60.1 | — |
| LiveBench | — | 44% |
Math GPT-5.2 leads
GPT-5.2: 59.8 (#32), Mistral Small: 15.4 (#287)
| Benchmark | GPT-5.2 | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 96.1% | 5.8% |
| LMArena Math | 1439 | 1341 |
| FrontierMath (Tiers 1-3) | 67.4% | — |
| FrontierMath Tier 4 | 31.7% | — |
| MathArena Final-Answer Competitions | 72% | — |
| ProofBench | 15% | — |
| LiveBench Math | — | 39.9% |
| MATH Level 5 | — | 46.8% |
| FrontierMath (Feb 2025 set) | 40.7% | — |
| FrontierMath Tier 4 (v1) | 18.8% | — |
Knowledge GPT-5.2 leads
GPT-5.2: 59.2 (#29), Mistral Small: 30.9 (#214)
| Benchmark | GPT-5.2 | Mistral Small |
|---|---|---|
| GPQA Diamond | 91.4% | 47.5% |
| Vectara Hallucination Rate | 8.4% | 5.1% |
| LMArena Expert | 1445 | 1293 |
| Humanity's Last Exam | 27.8% | — |
| SimpleQA Verified | 37.1% | — |
| MMLU | — | 68.7% |
Multimodal GPT-5.2 leads
GPT-5.2: 50.9 (#7), Mistral Small: 32.9 (#91)
| Benchmark | GPT-5.2 | Mistral Small |
|---|---|---|
| LMArena Vision | 1268 | 1142 |
| VPCT | 84% | — |
| Furniture Assembly | 38.3% | — |
| LMArena Document | 1405 | — |
Multilingual GPT-5.2 leads
GPT-5.2: 53.6 (#63), Mistral Small: 45.7 (#164)
| Benchmark | GPT-5.2 | Mistral Small |
|---|---|---|
| LMArena Non-English | 1425 | 1315 |
| LMArena Chinese | 1460 | 1342 |
| LMArena French | 1456 | 1337 |
| LMArena German | 1448 | 1341 |
| LMArena Japanese | 1421 | 1275 |
| LMArena Korean | 1390 | 1260 |
| LMArena Russian | 1440 | 1324 |
| LMArena Spanish | 1433 | 1346 |
Instruction Following GPT-5.2 leads
GPT-5.2: 74.9 (#83), Mistral Small: 66.6 (#204)
| Benchmark | GPT-5.2 | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1417 | 1310 |
| LiveBench Instruction Following | — | 63.7% |
Long Context GPT-5.2 leads
GPT-5.2: 44.0 (#74), Mistral Small: 40.4 (#151)
| Benchmark | GPT-5.2 | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1428 | 1327 |
| CL-bench | 18.2% | — |
Writing & Preference GPT-5.2 leads
GPT-5.2: 67.0 (#30), Mistral Small: 52.6 (#165)
| Benchmark | GPT-5.2 | Mistral Small |
|---|---|---|
| LMArena Text | 1439 | 1338 |
| LMArena Creative Writing | 1402 | 1304 |
| LMArena Multi-Turn | 1458 | 1344 |
| EQ-Bench Creative Writing | 1703 | — |
| LiveBench Language | — | 30.5% |
Frequently asked questions
Is GPT-5.2 better than Mistral Small?
GPT-5.2 is the stronger model overall, scoring 54.1 to 33.1 on the Noometry Index. Mistral Small costs 18× 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 Mistral Small?
Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; GPT-5.2 lists at $1.75 and $14.
Is GPT-5.2 or Mistral Small better for coding?
GPT-5.2 scores higher on coding benchmarks: 52.2 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
GPT-5.2 does, with 400K tokens against 256K.
How many benchmarks do GPT-5.2 and Mistral Small share?
26 benchmarks have published results for both models. GPT-5.2 has 67 scored results on Noometry and Mistral Small has 39.