Model comparison
GPT-5.6 Luna vs Mistral Small
GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 33.4 on the Noometry Index. Mistral Small costs 1.7× less per token, which makes it the better buy when GPT-5.6 Luna'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-5.6 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-5.6 Luna leads 77.7 to 16.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.3% for GPT-5.6 Luna and 5.8% for Mistral Small.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.20 / $1.20 for GPT-5.6 Luna.
- GPT-5.6 Luna accepts more context: 1.05M tokens versus 262K.
- Mistral Small has downloadable open weights; the other is API-only.
Side by side
| GPT-5.6 Luna | Mistral Small | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 54.6 | 33.4 |
| Released | 2026-07-09 | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 128K | 256K |
| Input $ / M tokens | $0.20 | $0.15 |
| Output $ / M tokens | $1.20 | $0.60 |
| Results tracked | 52 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.6 Luna leads
GPT-5.6 Luna: 54.5 (#28), Mistral Small: 34.0 (#247)
| Benchmark | GPT-5.6 Luna | Mistral Small |
|---|---|---|
| SciCode | 53.6% | 26.5% |
| LMArena Coding | 1466 | 1362 |
| ALE-Bench | 1,667 | 497.62 |
| DeepSWE | 67.2% | — |
| FrontierCode | 39.8% | — |
| CursorBench | 35.9% | — |
| LMArena WebDev | 1519 | — |
| WeirdML | 60.9% | — |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |
Agentic & Tool Use GPT-5.6 Luna leads
GPT-5.6 Luna: 34.4 (#45), Mistral Small: 28.1 (#93)
| Benchmark | GPT-5.6 Luna | Mistral Small |
|---|---|---|
| APEX-Agents | 43% | — |
| Berkeley Function Calling Leaderboard | — | 37.1% |
| BALROG | 45.6% | — |
| GDP.pdf | 22.7% | — |
| Vending-Bench 2 | 4,095 | — |
Reasoning GPT-5.6 Luna leads
GPT-5.6 Luna: 47.6 (#43), Mistral Small: 19.8 (#250)
| Benchmark | GPT-5.6 Luna | Mistral Small |
|---|---|---|
| Kagi LLM Benchmark | 49.1% | 37.8% |
| CritPt | 20.6% | 0% |
| LMArena Hard Prompts | 1451 | 1335 |
| DTBench | 89.1% | 70.9% |
| LMCA | 48.5% | 20.6% |
| ARC-AGI-2 | 59.5% | — |
| SimpleBench | 46.8% | — |
| NYT Connections (extended) | 69.4% | — |
| ARC-AGI-1 | 88% | — |
| Chess Puzzles | 40% | — |
| LiveBench Reasoning | — | 44.8% |
| Mystery Game Puzzles | 21% | — |
| LiveBench Data Analysis | — | 53.7% |
| Surface Evolver Bench | 61.9% | — |
| Epoch Capabilities Index | 156.39 | — |
| LiveBench | — | 44% |
Math GPT-5.6 Luna leads
GPT-5.6 Luna: 77.7 (#14), Mistral Small: 16.4 (#293)
| Benchmark | GPT-5.6 Luna | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.3% | 5.8% |
| LMArena Math | 1458 | 1341 |
| FrontierMath (Tiers 1-3) | 82.1% | — |
| FrontierMath Tier 4 | 61% | — |
| ProofBench | 60% | — |
| LiveBench Math | — | 39.9% |
| MATH Level 5 | — | 46.8% |
Knowledge GPT-5.6 Luna leads
GPT-5.6 Luna: 58.5 (#34), Mistral Small: 31.0 (#222)
| Benchmark | GPT-5.6 Luna | Mistral Small |
|---|---|---|
| GPQA Diamond | 91.6% | 47.5% |
| LMArena Expert | 1478 | 1291 |
| SimpleQA Verified | 41% | — |
| Vectara Hallucination Rate | — | 5.1% |
| MMLU | — | 68.7% |
Multimodal GPT-5.6 Luna leads
GPT-5.6 Luna: 42.7 (#28), Mistral Small: 33.5 (#96)
| Benchmark | GPT-5.6 Luna | Mistral Small |
|---|---|---|
| LMArena Vision | 1258 | 1142 |
| Blueprint-Bench 2 | 22.6% | — |
| Furniture Assembly | 42.5% | — |
| LMArena Document | 1457 | — |
Multilingual GPT-5.6 Luna leads
GPT-5.6 Luna: 52.8 (#78), Mistral Small: 45.5 (#169)
| Benchmark | GPT-5.6 Luna | Mistral Small |
|---|---|---|
| LMArena Non-English | 1417 | 1315 |
| LMArena Chinese | 1470 | 1340 |
| LMArena French | 1456 | 1337 |
| LMArena German | 1454 | 1340 |
| LMArena Japanese | 1411 | 1275 |
| LMArena Korean | 1415 | 1259 |
| LMArena Russian | 1428 | 1324 |
| LMArena Spanish | 1448 | 1346 |
Instruction Following GPT-5.6 Luna leads
GPT-5.6 Luna: 75.6 (#57), Mistral Small: 66.4 (#209)
| Benchmark | GPT-5.6 Luna | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1437 | 1310 |
| LiveBench Instruction Following | — | 63.7% |
Long Context GPT-5.6 Luna leads
GPT-5.6 Luna: 43.9 (#82), Mistral Small: 40.4 (#156)
| Benchmark | GPT-5.6 Luna | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1436 | 1327 |
Writing & Preference GPT-5.6 Luna leads
GPT-5.6 Luna: 68.0 (#29), Mistral Small: 52.5 (#171)
| Benchmark | GPT-5.6 Luna | Mistral Small |
|---|---|---|
| LMArena Text | 1431 | 1338 |
| LMArena Creative Writing | 1396 | 1305 |
| LMArena Multi-Turn | 1434 | 1344 |
| EQ-Bench Creative Writing | 1829 | — |
| EQ-Bench 4 | 1156 | — |
| LiveBench Language | — | 30.5% |
Frequently asked questions
Is GPT-5.6 Luna better than Mistral Small?
GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 33.4 on the Noometry Index. Mistral Small costs 1.7× less per token, which makes it the better buy when GPT-5.6 Luna's lead doesn't matter for your workload.
Which is cheaper, GPT-5.6 Luna or Mistral Small?
Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; GPT-5.6 Luna lists at $0.20 and $1.20.
Is GPT-5.6 Luna or Mistral Small better for coding?
GPT-5.6 Luna scores higher on coding benchmarks: 54.5 versus 34.0 in the Noometry coding category.
Which has the bigger context window?
GPT-5.6 Luna does, with 1.05M tokens against 262K.
How many benchmarks do GPT-5.6 Luna and Mistral Small share?
26 benchmarks have published results for both models. GPT-5.6 Luna has 52 scored results on Noometry and Mistral Small has 39.