# GPT-6 Astra vs Mistral Small

> GPT-6 Astra is the stronger model overall, scoring 70.3 to 33.1 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.

- Canonical page: https://noometry.com/compare/gpt-6-astra-vs-mistral-small
- Last updated: 2026-10-10
- Shared benchmarks: 23

## Summary

- They share 23 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 93.4 to 15.4.
- 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 256K.
- Mistral Small has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-6 Astra | Mistral Small |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 70.3 | 33.1 |
| Rank | 1 | 238 |
| Context | 1.05M | 256K |
| Input $/M | $10 | $0.15 |
| Output $/M | $50 | $0.60 |
| Weights | Proprietary | Open |

## Coding

- GPT-6 Astra: 70.5 (#3)
- Mistral Small: 33.5 (#242)

| Benchmark | GPT-6 Astra | Mistral Small |
|---|---|---|
| SciCode | 56.5% | 26.5% |
| LMArena Coding | 1488 | 1363 |
| ALE-Bench | 2,951 | 497.62 |
| DeepSWE | 74.1% | — |
| FrontierCode | 53.3% | — |
| LMArena WebDev | 1792 | — |
| FrontierSWE | 65.5% | — |
| WeirdML | 93.6% | — |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| MirrorCode | 46.7% | — |
| BigCodeBench Complete | — | 46.6% |

## Agentic & Tool Use

- GPT-6 Astra: 52.3 (#3)
- Mistral Small: 27.9 (#87)

| Benchmark | GPT-6 Astra | Mistral Small |
|---|---|---|
| APEX-Agents | 64.7% | — |
| Berkeley Function Calling Leaderboard | — | 37.1% |
| Remote Labor Index | 20.8% | — |
| BALROG | 68.3% | — |
| Vending-Bench 2 | 15,515 | — |

## Reasoning

- GPT-6 Astra: 85.1 (#1)
- Mistral Small: 19.3 (#238)

| Benchmark | GPT-6 Astra | Mistral Small |
|---|---|---|
| CritPt | 31.7% | 0% |
| LMArena Hard Prompts | 1464 | 1336 |
| 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 | 166.6 | — |
| LiveBench | — | 44% |

## Math

- GPT-6 Astra: 93.4 (#1)
- Mistral Small: 15.4 (#287)

| Benchmark | GPT-6 Astra | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 5.8% |
| LMArena Math | 1463 | 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: 75.3 (#1)
- Mistral Small: 30.9 (#214)

| Benchmark | GPT-6 Astra | Mistral Small |
|---|---|---|
| GPQA Diamond | 95.8% | 47.5% |
| Vectara Hallucination Rate | 8.7% | 5.1% |
| LMArena Expert | 1486 | 1293 |
| Humanity's Last Exam | 54.8% | — |
| SimpleQA Verified | 75.6% | — |
| MMLU | — | 68.7% |

## Multimodal

- GPT-6 Astra: 55.1 (#3)
- Mistral Small: 32.9 (#91)

| Benchmark | GPT-6 Astra | Mistral Small |
|---|---|---|
| LMArena Vision | 1280 | 1142 |
| Blueprint-Bench 2 | 49.7% | — |
| Furniture Assembly | 80% | — |
| LMArena Document | 1468 | — |

## Multilingual

- GPT-6 Astra: 54.0 (#53)
- Mistral Small: 45.7 (#164)

| Benchmark | GPT-6 Astra | Mistral Small |
|---|---|---|
| LMArena Non-English | 1431 | 1315 |
| LMArena Chinese | 1495 | 1342 |
| LMArena French | 1467 | 1337 |
| LMArena Russian | 1434 | 1324 |
| LMArena Spanish | 1412 | 1346 |
| LMArena German | — | 1341 |
| LMArena Japanese | — | 1275 |
| LMArena Korean | — | 1260 |

## Instruction Following

- GPT-6 Astra: 76.6 (#37)
- Mistral Small: 66.6 (#204)

| Benchmark | GPT-6 Astra | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1454 | 1310 |
| LiveBench Instruction Following | — | 63.7% |

## Long Context

- GPT-6 Astra: 44.7 (#57)
- Mistral Small: 40.4 (#151)

| Benchmark | GPT-6 Astra | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1460 | 1327 |

## Writing & Preference

- GPT-6 Astra: 75.7 (#7)
- Mistral Small: 52.6 (#165)

| Benchmark | GPT-6 Astra | Mistral Small |
|---|---|---|
| LMArena Text | 1443 | 1338 |
| LMArena Creative Writing | 1423 | 1304 |
| LMArena Multi-Turn | 1457 | 1344 |
| EQ-Bench Creative Writing | 2173 | — |
| LiveBench Language | — | 30.5% |

## FAQ

### Is GPT-6 Astra better than Mistral Small?

GPT-6 Astra is the stronger model overall, scoring 70.3 to 33.1 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: 70.5 versus 33.5 in the Noometry coding category.

### Which has the bigger context window?

GPT-6 Astra does, with 1.05M tokens against 256K.

### How many benchmarks do GPT-6 Astra and Mistral Small share?

23 benchmarks have published results for both models. GPT-6 Astra has 51 scored results on Noometry and Mistral Small has 39.