Model comparison
GPT-5.6 Terra vs Mistral Small
GPT-5.6 Terra is the stronger model overall, scoring 59.2 to 33.4 on the Noometry Index. Mistral Small costs 17× less per token, which makes it the better buy when GPT-5.6 Terra'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 Terra 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 Terra leads 81.6 to 16.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 99.7% for GPT-5.6 Terra and 5.8% for Mistral Small.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $2 / $12 for GPT-5.6 Terra.
- GPT-5.6 Terra 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 Terra | Mistral Small | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 59.2 | 33.4 |
| Released | 2026-07-09 | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 128K | 256K |
| Input $ / M tokens | $2 | $0.15 |
| Output $ / M tokens | $12 | $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 Terra leads
GPT-5.6 Terra: 57.7 (#19), Mistral Small: 34.0 (#247)
| Benchmark | GPT-5.6 Terra | Mistral Small |
|---|---|---|
| SciCode | 55% | 26.5% |
| LMArena Coding | 1484 | 1362 |
| ALE-Bench | 1,951 | 497.62 |
| DeepSWE | 69.6% | — |
| FrontierCode | 41.3% | — |
| CursorBench | 41.3% | — |
| LMArena WebDev | 1522 | — |
| WeirdML | 78.3% | — |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |
Agentic & Tool Use GPT-5.6 Terra leads
GPT-5.6 Terra: 40.1 (#25), Mistral Small: 28.1 (#93)
| Benchmark | GPT-5.6 Terra | Mistral Small |
|---|---|---|
| APEX-Agents | 58.2% | — |
| Berkeley Function Calling Leaderboard | — | 37.1% |
| BALROG | 53.2% | — |
| GDP.pdf | 24.7% | — |
| Vending-Bench 2 | 7,343 | — |
Reasoning GPT-5.6 Terra leads
GPT-5.6 Terra: 60.7 (#21), Mistral Small: 19.8 (#250)
| Benchmark | GPT-5.6 Terra | Mistral Small |
|---|---|---|
| Kagi LLM Benchmark | 51.3% | 37.8% |
| CritPt | 30% | 0% |
| LMArena Hard Prompts | 1468 | 1335 |
| DTBench | 93.3% | 70.9% |
| LMCA | 55% | 20.6% |
| ARC-AGI-2 | 83.9% | — |
| SimpleBench | 48.9% | — |
| NYT Connections (extended) | 78.4% | — |
| ARC-AGI-1 | 96.5% | — |
| Chess Puzzles | 54% | — |
| LiveBench Reasoning | — | 44.8% |
| Mystery Game Puzzles | 35% | — |
| LiveBench Data Analysis | — | 53.7% |
| Surface Evolver Bench | 83.8% | — |
| Epoch Capabilities Index | 159.62 | — |
| LiveBench | — | 44% |
Math GPT-5.6 Terra leads
GPT-5.6 Terra: 81.6 (#12), Mistral Small: 16.4 (#293)
| Benchmark | GPT-5.6 Terra | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 99.7% | 5.8% |
| LMArena Math | 1466 | 1341 |
| FrontierMath (Tiers 1-3) | 86% | — |
| FrontierMath Tier 4 | 70.7% | — |
| ProofBench | 74% | — |
| LiveBench Math | — | 39.9% |
| MATH Level 5 | — | 46.8% |
Knowledge GPT-5.6 Terra leads
GPT-5.6 Terra: 61.2 (#30), Mistral Small: 31.0 (#222)
| Benchmark | GPT-5.6 Terra | Mistral Small |
|---|---|---|
| GPQA Diamond | 93.3% | 47.5% |
| LMArena Expert | 1492 | 1291 |
| SimpleQA Verified | 43.2% | — |
| Vectara Hallucination Rate | — | 5.1% |
| MMLU | — | 68.7% |
Multimodal GPT-5.6 Terra leads
GPT-5.6 Terra: 47.3 (#11), Mistral Small: 33.5 (#96)
| Benchmark | GPT-5.6 Terra | Mistral Small |
|---|---|---|
| LMArena Vision | 1271 | 1142 |
| Blueprint-Bench 2 | 30.8% | — |
| Furniture Assembly | 54.2% | — |
| LMArena Document | 1472 | — |
Multilingual GPT-5.6 Terra leads
GPT-5.6 Terra: 54.4 (#44), Mistral Small: 45.5 (#169)
| Benchmark | GPT-5.6 Terra | Mistral Small |
|---|---|---|
| LMArena Non-English | 1439 | 1315 |
| LMArena Chinese | 1513 | 1340 |
| LMArena French | 1471 | 1337 |
| LMArena German | 1460 | 1340 |
| LMArena Japanese | 1457 | 1275 |
| LMArena Korean | 1425 | 1259 |
| LMArena Russian | 1450 | 1324 |
| LMArena Spanish | 1448 | 1346 |
Instruction Following GPT-5.6 Terra leads
GPT-5.6 Terra: 76.4 (#40), Mistral Small: 66.4 (#209)
| Benchmark | GPT-5.6 Terra | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1454 | 1310 |
| LiveBench Instruction Following | — | 63.7% |
Long Context GPT-5.6 Terra leads
GPT-5.6 Terra: 44.4 (#68), Mistral Small: 40.4 (#156)
| Benchmark | GPT-5.6 Terra | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1451 | 1327 |
Writing & Preference GPT-5.6 Terra leads
GPT-5.6 Terra: 70.2 (#23), Mistral Small: 52.5 (#171)
| Benchmark | GPT-5.6 Terra | Mistral Small |
|---|---|---|
| LMArena Text | 1447 | 1338 |
| LMArena Creative Writing | 1410 | 1305 |
| LMArena Multi-Turn | 1449 | 1344 |
| EQ-Bench Creative Writing | 1855 | — |
| EQ-Bench 4 | 1234 | — |
| LiveBench Language | — | 30.5% |
Frequently asked questions
Is GPT-5.6 Terra better than Mistral Small?
GPT-5.6 Terra is the stronger model overall, scoring 59.2 to 33.4 on the Noometry Index. Mistral Small costs 17× less per token, which makes it the better buy when GPT-5.6 Terra's lead doesn't matter for your workload.
Which is cheaper, GPT-5.6 Terra 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 Terra lists at $2 and $12.
Is GPT-5.6 Terra or Mistral Small better for coding?
GPT-5.6 Terra scores higher on coding benchmarks: 57.7 versus 34.0 in the Noometry coding category.
Which has the bigger context window?
GPT-5.6 Terra does, with 1.05M tokens against 262K.
How many benchmarks do GPT-5.6 Terra and Mistral Small share?
26 benchmarks have published results for both models. GPT-5.6 Terra has 52 scored results on Noometry and Mistral Small has 39.