Model comparison
GPT-6 Luna vs Mistral Large 3
GPT-6 Luna is the stronger model overall, scoring 53.3 to 39.1 on the Noometry Index.
Last verified . 20 shared benchmarks.
Mistral AISummary
- They share 20 benchmarks with published results for both. GPT-6 Luna scores higher in 6 categories and Mistral Large 3 in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Luna leads 76.1 to 38.7.
- The biggest single-benchmark swing is NYT Connections (extended): 68.7% for GPT-6 Luna and 7.5% for Mistral Large 3.
- GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $0.25 / $0.75 for Mistral Large 3.
- GPT-6 Luna accepts more context: 1.05M tokens versus 262K.
- Mistral Large 3 has downloadable open weights; the other is API-only.
Side by side
| GPT-6 Luna | Mistral Large 3 | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 53.3 | 39.1 |
| Released | 2026-09-22 | 2025-12-02 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 128K | 8K |
| Input $ / M tokens | $0.10 | $0.25 |
| Output $ / M tokens | $0.50 | $0.75 |
| Results tracked | 42 | 24 |
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 Large 3: 34.4 (#237)
| Benchmark | GPT-6 Luna | Mistral Large 3 |
|---|---|---|
| LMArena WebDev | 1581 | 1230 |
| LMArena Coding | 1439 | 1448 |
| DeepSWE | 66.6% | — |
| FrontierCode | 42.4% | — |
| SciCode | 54.6% | — |
| ALE-Bench | 1,577 | — |
Agentic & Tool Use Not comparable
GPT-6 Luna: 33.3 (#54), Mistral Large 3: —
| Benchmark | GPT-6 Luna | Mistral Large 3 |
|---|---|---|
| APEX-Agents | 44.3% | — |
| GDP.pdf | 23% | — |
Reasoning GPT-6 Luna leads
GPT-6 Luna: 48.2 (#41), Mistral Large 3: 15.2 (#319)
| Benchmark | GPT-6 Luna | Mistral Large 3 |
|---|---|---|
| NYT Connections (extended) | 68.7% | 7.5% |
| LMArena Hard Prompts | 1411 | 1429 |
| ARC-AGI-2 | 59.3% | — |
| Kagi LLM Benchmark | — | 50.9% |
| ARC-AGI-1 | 86.7% | — |
| CritPt | 19.4% | — |
| Chess Puzzles | 31% | — |
| Thematic Generalization | — | 23% |
| Mystery Game Puzzles | 7% | — |
| DTBench | 90.1% | — |
| LMCA | 44.5% | — |
| Epoch Capabilities Index | 156.28 | — |
Math GPT-6 Luna leads
GPT-6 Luna: 76.1 (#15), Mistral Large 3: 38.7 (#129)
| Benchmark | GPT-6 Luna | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1416 | 1414 |
| FrontierMath (Tiers 1-3) | 78.9% | — |
| FrontierMath Tier 4 | 56.1% | — |
| OTIS Mock AIME 2024-2025 | 98.9% | — |
| ProofBench | 64% | — |
Knowledge GPT-6 Luna leads
GPT-6 Luna: 57.0 (#41), Mistral Large 3: 36.0 (#177)
| Benchmark | GPT-6 Luna | Mistral Large 3 |
|---|---|---|
| LMArena Expert | 1444 | 1421 |
| GPQA Diamond | 90.5% | — |
| SimpleQA Verified | 41.4% | — |
| Vectara Hallucination Rate | — | 14.5% |
Multimodal GPT-6 Luna leads
GPT-6 Luna: 42.4 (#30), Mistral Large 3: 38.2 (#66)
| Benchmark | GPT-6 Luna | Mistral Large 3 |
|---|---|---|
| LMArena Vision | 1217 | 1221 |
| Blueprint-Bench 2 | 31.2% | — |
| Furniture Assembly | 44.2% | — |
Multilingual Mistral Large 3 leads
GPT-6 Luna: 50.5 (#117), Mistral Large 3: 52.5 (#84)
| Benchmark | GPT-6 Luna | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1386 | 1413 |
| LMArena Chinese | 1433 | 1447 |
| LMArena French | 1420 | 1455 |
| LMArena German | 1369 | 1437 |
| LMArena Japanese | 1369 | 1394 |
| LMArena Korean | 1360 | 1384 |
| LMArena Russian | 1394 | 1411 |
| LMArena Spanish | 1393 | 1440 |
Instruction Following Too close to call
GPT-6 Luna: 74.3 (#99), Mistral Large 3: 74.0 (#108)
| Benchmark | GPT-6 Luna | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1409 | 1403 |
Long Context Too close to call
GPT-6 Luna: 43.0 (#111), Mistral Large 3: 43.1 (#105)
| Benchmark | GPT-6 Luna | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1409 | 1413 |
Writing & Preference Mistral Large 3 leads
GPT-6 Luna: 58.3 (#119), Mistral Large 3: 60.0 (#101)
| Benchmark | GPT-6 Luna | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1391 | 1428 |
| LMArena Creative Writing | 1363 | 1386 |
| LMArena Multi-Turn | 1396 | 1429 |
| EQ-Bench Creative Writing | — | 1412 |
Frequently asked questions
Is GPT-6 Luna better than Mistral Large 3?
GPT-6 Luna is the stronger model overall, scoring 53.3 to 39.1 on the Noometry Index.
Which is cheaper, GPT-6 Luna or Mistral Large 3?
GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; Mistral Large 3 lists at $0.25 and $0.75.
Is GPT-6 Luna or Mistral Large 3 better for coding?
GPT-6 Luna scores higher on coding benchmarks: 55.5 versus 34.4 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 Large 3 share?
20 benchmarks have published results for both models. GPT-6 Luna has 42 scored results on Noometry and Mistral Large 3 has 24.