Model comparison
GPT-6 Luna vs Mistral Small
GPT-6 Luna is the stronger model overall, scoring 53.3 to 33.4 on the Noometry Index.
Last verified . 25 shared benchmarks.
Mistral AISummary
- They share 25 benchmarks with published results for both. GPT-6 Luna 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 Luna leads 76.1 to 16.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.9% for GPT-6 Luna and 5.8% for Mistral Small.
- GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $0.15 / $0.60 for Mistral Small.
- GPT-6 Luna accepts more context: 1.05M tokens versus 262K.
- Mistral Small has downloadable open weights; the other is API-only.
Side by side
| GPT-6 Luna | Mistral Small | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 53.3 | 33.4 |
| Released | 2026-09-22 | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 128K | 256K |
| Input $ / M tokens | $0.10 | $0.15 |
| Output $ / M tokens | $0.50 | $0.60 |
| Results tracked | 42 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Luna leads
GPT-6 Luna: 55.5 (#25), Mistral Small: 34.0 (#247)
| Benchmark | GPT-6 Luna | Mistral Small |
|---|---|---|
| SciCode | 54.6% | 26.5% |
| LMArena Coding | 1439 | 1362 |
| ALE-Bench | 1,577 | 497.62 |
| DeepSWE | 66.6% | — |
| FrontierCode | 42.4% | — |
| LMArena WebDev | 1581 | — |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |
Agentic & Tool Use GPT-6 Luna leads
GPT-6 Luna: 33.3 (#54), Mistral Small: 28.1 (#93)
| Benchmark | GPT-6 Luna | Mistral Small |
|---|---|---|
| APEX-Agents | 44.3% | — |
| Berkeley Function Calling Leaderboard | — | 37.1% |
| GDP.pdf | 23% | — |
Reasoning GPT-6 Luna leads
GPT-6 Luna: 48.2 (#41), Mistral Small: 19.8 (#250)
| Benchmark | GPT-6 Luna | Mistral Small |
|---|---|---|
| CritPt | 19.4% | 0% |
| LMArena Hard Prompts | 1411 | 1335 |
| DTBench | 90.1% | 70.9% |
| LMCA | 44.5% | 20.6% |
| ARC-AGI-2 | 59.3% | — |
| Kagi LLM Benchmark | — | 37.8% |
| NYT Connections (extended) | 68.7% | — |
| ARC-AGI-1 | 86.7% | — |
| Chess Puzzles | 31% | — |
| LiveBench Reasoning | — | 44.8% |
| Mystery Game Puzzles | 7% | — |
| LiveBench Data Analysis | — | 53.7% |
| Epoch Capabilities Index | 156.28 | — |
| LiveBench | — | 44% |
Math GPT-6 Luna leads
GPT-6 Luna: 76.1 (#15), Mistral Small: 16.4 (#293)
| Benchmark | GPT-6 Luna | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.9% | 5.8% |
| LMArena Math | 1416 | 1341 |
| FrontierMath (Tiers 1-3) | 78.9% | — |
| FrontierMath Tier 4 | 56.1% | — |
| ProofBench | 64% | — |
| LiveBench Math | — | 39.9% |
| MATH Level 5 | — | 46.8% |
Knowledge GPT-6 Luna leads
GPT-6 Luna: 57.0 (#41), Mistral Small: 31.0 (#222)
| Benchmark | GPT-6 Luna | Mistral Small |
|---|---|---|
| GPQA Diamond | 90.5% | 47.5% |
| LMArena Expert | 1444 | 1291 |
| SimpleQA Verified | 41.4% | — |
| Vectara Hallucination Rate | — | 5.1% |
| MMLU | — | 68.7% |
Multimodal GPT-6 Luna leads
GPT-6 Luna: 42.4 (#30), Mistral Small: 33.5 (#96)
| Benchmark | GPT-6 Luna | Mistral Small |
|---|---|---|
| LMArena Vision | 1217 | 1142 |
| Blueprint-Bench 2 | 31.2% | — |
| Furniture Assembly | 44.2% | — |
Multilingual GPT-6 Luna leads
GPT-6 Luna: 50.5 (#117), Mistral Small: 45.5 (#169)
| Benchmark | GPT-6 Luna | Mistral Small |
|---|---|---|
| LMArena Non-English | 1386 | 1315 |
| LMArena Chinese | 1433 | 1340 |
| LMArena French | 1420 | 1337 |
| LMArena German | 1369 | 1340 |
| LMArena Japanese | 1369 | 1275 |
| LMArena Korean | 1360 | 1259 |
| LMArena Russian | 1394 | 1324 |
| LMArena Spanish | 1393 | 1346 |
Instruction Following GPT-6 Luna leads
GPT-6 Luna: 74.3 (#99), Mistral Small: 66.4 (#209)
| Benchmark | GPT-6 Luna | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1409 | 1310 |
| LiveBench Instruction Following | — | 63.7% |
Long Context GPT-6 Luna leads
GPT-6 Luna: 43.0 (#111), Mistral Small: 40.4 (#156)
| Benchmark | GPT-6 Luna | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1409 | 1327 |
Writing & Preference GPT-6 Luna leads
GPT-6 Luna: 58.3 (#119), Mistral Small: 52.5 (#171)
| Benchmark | GPT-6 Luna | Mistral Small |
|---|---|---|
| LMArena Text | 1391 | 1338 |
| LMArena Creative Writing | 1363 | 1305 |
| LMArena Multi-Turn | 1396 | 1344 |
| LiveBench Language | — | 30.5% |
Frequently asked questions
Is GPT-6 Luna better than Mistral Small?
GPT-6 Luna is the stronger model overall, scoring 53.3 to 33.4 on the Noometry Index.
Which is cheaper, GPT-6 Luna or Mistral Small?
GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; Mistral Small lists at $0.15 and $0.60.
Is GPT-6 Luna or Mistral Small better for coding?
GPT-6 Luna scores higher on coding benchmarks: 55.5 versus 34.0 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Luna does, with 1.05M tokens against 262K.
How many benchmarks do GPT-6 Luna and Mistral Small share?
25 benchmarks have published results for both models. GPT-6 Luna has 42 scored results on Noometry and Mistral Small has 39.