Model comparison
GPT-6 Astra vs Mistral Small
GPT-6 Astra is the stronger model overall, scoring 70.8 to 33.4 on the Noometry Index. Mistral Small costs 76× less per token, which makes it the better buy when GPT-6 Astra'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-6 Astra 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-6 Astra leads 93.5 to 16.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 100% for GPT-6 Astra and 5.8% for Mistral Small.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $10 / $50 for GPT-6 Astra.
- GPT-6 Astra accepts more context: 1.05M tokens versus 262K.
- Mistral Small has downloadable open weights; the other is API-only.
Side by side
| GPT-6 Astra | Mistral Small | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 70.8 | 33.4 |
| Released | 2026-09-03 | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 128K | 256K |
| Input $ / M tokens | $10 | $0.15 |
| Output $ / M tokens | $50 | $0.60 |
| Results tracked | 56 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Astra leads
GPT-6 Astra: 73.7 (#2), Mistral Small: 34.0 (#247)
| Benchmark | GPT-6 Astra | Mistral Small |
|---|---|---|
| SciCode | 56.5% | 26.5% |
| LMArena Coding | 1487 | 1362 |
| ALE-Bench | 2,951 | 497.62 |
| DeepSWE | 74.1% | — |
| FrontierCode | 53.3% | — |
| LMArena WebDev | 1786 | — |
| FrontierSWE | 65.5% | — |
| GSO | 79.4% | — |
| WeirdML | 93.6% | — |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| MirrorCode | 46.7% | — |
| BigCodeBench Complete | — | 46.6% |
Agentic & Tool Use GPT-6 Astra leads
GPT-6 Astra: 52.9 (#3), Mistral Small: 28.1 (#93)
| Benchmark | GPT-6 Astra | Mistral Small |
|---|---|---|
| APEX-Agents | 64.7% | — |
| Berkeley Function Calling Leaderboard | — | 37.1% |
| Remote Labor Index | 20.8% | — |
| BALROG | 68.3% | — |
| GDP.pdf | 34.2% | — |
| Vending-Bench 2 | 15,515 | — |
Reasoning GPT-6 Astra leads
GPT-6 Astra: 85.1 (#1), Mistral Small: 19.8 (#250)
| Benchmark | GPT-6 Astra | Mistral Small |
|---|---|---|
| CritPt | 31.7% | 0% |
| LMArena Hard Prompts | 1462 | 1335 |
| DTBench | 97.3% | 70.9% |
| LMCA | 64.4% | 20.6% |
| ARC-AGI-2 | 95% | — |
| Kagi LLM Benchmark | — | 37.8% |
| NYT Connections (extended) | 98.1% | — |
| ARC-AGI-1 | 98.5% | — |
| Chess Puzzles | 72% | — |
| EBR-Bench | 76.2% | — |
| LiveBench Reasoning | — | 44.8% |
| Mystery Game Puzzles | 84% | — |
| LiveBench Data Analysis | — | 53.7% |
| Bench to the Future 3 | 0.14 | — |
| Epoch Capabilities Index | 166.45 | — |
| LiveBench | — | 44% |
Math GPT-6 Astra leads
GPT-6 Astra: 93.5 (#2), Mistral Small: 16.4 (#293)
| Benchmark | GPT-6 Astra | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 5.8% |
| LMArena Math | 1465 | 1341 |
| FrontierMath (Tiers 1-3) | 93.7% | — |
| FrontierMath Tier 4 | 97.6% | — |
| ProofBench | 99% | — |
| LiveBench Math | — | 39.9% |
| MATH Level 5 | — | 46.8% |
| FrontierMath Erdős | 2.9% | — |
Knowledge GPT-6 Astra leads
GPT-6 Astra: 75.3 (#1), Mistral Small: 31.0 (#222)
| Benchmark | GPT-6 Astra | Mistral Small |
|---|---|---|
| GPQA Diamond | 95.8% | 47.5% |
| Vectara Hallucination Rate | 8.7% | 5.1% |
| LMArena Expert | 1483 | 1291 |
| Humanity's Last Exam | 54.8% | — |
| SimpleQA Verified | 75.6% | — |
| MMLU | — | 68.7% |
Multimodal GPT-6 Astra leads
GPT-6 Astra: 55.0 (#3), Mistral Small: 33.5 (#96)
| Benchmark | GPT-6 Astra | Mistral Small |
|---|---|---|
| LMArena Vision | 1281 | 1142 |
| Blueprint-Bench 2 | 49.7% | — |
| Furniture Assembly | 80% | — |
| LMArena Document | 1468 | — |
Multilingual GPT-6 Astra leads
GPT-6 Astra: 53.7 (#61), Mistral Small: 45.5 (#169)
| Benchmark | GPT-6 Astra | Mistral Small |
|---|---|---|
| LMArena Non-English | 1430 | 1315 |
| LMArena Chinese | 1484 | 1340 |
| LMArena French | 1456 | 1337 |
| LMArena German | 1440 | 1340 |
| LMArena Japanese | 1379 | 1275 |
| LMArena Korean | 1426 | 1259 |
| LMArena Russian | 1436 | 1324 |
| LMArena Spanish | 1407 | 1346 |
Instruction Following GPT-6 Astra leads
GPT-6 Astra: 76.3 (#44), Mistral Small: 66.4 (#209)
| Benchmark | GPT-6 Astra | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1450 | 1310 |
| LiveBench Instruction Following | — | 63.7% |
Long Context GPT-6 Astra leads
GPT-6 Astra: 44.5 (#62), Mistral Small: 40.4 (#156)
| Benchmark | GPT-6 Astra | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1456 | 1327 |
Writing & Preference GPT-6 Astra leads
GPT-6 Astra: 75.3 (#7), Mistral Small: 52.5 (#171)
| Benchmark | GPT-6 Astra | Mistral Small |
|---|---|---|
| LMArena Text | 1441 | 1338 |
| LMArena Creative Writing | 1418 | 1305 |
| LMArena Multi-Turn | 1448 | 1344 |
| EQ-Bench Creative Writing | 2173 | — |
| LiveBench Language | — | 30.5% |
Frequently asked questions
Is GPT-6 Astra better than Mistral Small?
GPT-6 Astra is the stronger model overall, scoring 70.8 to 33.4 on the Noometry Index. Mistral Small costs 76× less per token, which makes it the better buy when GPT-6 Astra's lead doesn't matter for your workload.
Which is cheaper, GPT-6 Astra or Mistral Small?
Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; GPT-6 Astra lists at $10 and $50.
Is GPT-6 Astra or Mistral Small better for coding?
GPT-6 Astra scores higher on coding benchmarks: 73.7 versus 34.0 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Astra does, with 1.05M tokens against 262K.
How many benchmarks do GPT-6 Astra and Mistral Small share?
26 benchmarks have published results for both models. GPT-6 Astra has 56 scored results on Noometry and Mistral Small has 39.