Model comparison
GPT-5.6 Terra vs Magistral Medium
GPT-5.6 Terra is the stronger model overall, scoring 59.1 to 34.8 on the Noometry Index. Magistral Medium costs 1.6× less per token, which makes it the better buy when GPT-5.6 Terra's lead doesn't matter for your workload.
Last verified . 22 shared benchmarks.
Mistral AISummary
- They share 22 benchmarks with published results for both. GPT-5.6 Terra scores higher in 8 categories and Magistral Medium in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.6 Terra leads 60.6 to 8.7.
- The biggest single-benchmark swing is ARC-AGI-1: 96.5% for GPT-5.6 Terra and 6.1% for Magistral Medium.
- Magistral Medium is cheaper at $2 / $5 per million input/output tokens, against $2 / $12 for GPT-5.6 Terra.
- GPT-5.6 Terra accepts more context: 1.05M tokens versus 128K.
- Magistral Medium has downloadable open weights; the other is API-only.
Side by side
| GPT-5.6 Terra | Magistral Medium | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 59.1 | 34.8 |
| Released | 2026-07-09 | 2025-03-17 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 128K |
| Max output | 128K | 16K |
| Input $ / M tokens | $2 | $2 |
| Output $ / M tokens | $12 | $5 |
| Results tracked | 52 | 22 |
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: 57.1 (#16), Magistral Medium: 38.6 (#161)
| Benchmark | GPT-5.6 Terra | Magistral Medium |
|---|---|---|
| SciCode | 55% | 39.2% |
| LMArena Coding | 1484 | 1319 |
| DeepSWE | 69.6% | — |
| FrontierCode | 41.3% | — |
| CursorBench | 41.3% | — |
| LMArena WebDev | 1520 | — |
| WeirdML | 78.3% | — |
| ALE-Bench | 1,951 | — |
Agentic & Tool Use Not comparable
GPT-5.6 Terra: 40.2 (#23), Magistral Medium: —
| Benchmark | GPT-5.6 Terra | Magistral Medium |
|---|---|---|
| APEX-Agents | 58.2% | — |
| BALROG | 53.2% | — |
| GDP.pdf | 24.7% | — |
| Vending-Bench 2 | 7,343 | — |
Reasoning GPT-5.6 Terra leads
GPT-5.6 Terra: 60.6 (#19), Magistral Medium: 8.7 (#342)
| Benchmark | GPT-5.6 Terra | Magistral Medium |
|---|---|---|
| ARC-AGI-2 | 83.9% | 0% |
| Kagi LLM Benchmark | 51.3% | 16.2% |
| ARC-AGI-1 | 96.5% | 6.1% |
| CritPt | 30% | 0.3% |
| LMArena Hard Prompts | 1467 | 1267 |
| SimpleBench | 48.9% | — |
| NYT Connections (extended) | 78.4% | — |
| Chess Puzzles | 54% | — |
| Mystery Game Puzzles | 35% | — |
| DTBench | 93.3% | — |
| LMCA | 55% | — |
| Surface Evolver Bench | 83.8% | — |
| Epoch Capabilities Index | 159.31 | — |
Math GPT-5.6 Terra leads
GPT-5.6 Terra: 81.5 (#10), Magistral Medium: 32.4 (#187)
| Benchmark | GPT-5.6 Terra | Magistral Medium |
|---|---|---|
| LMArena Math | 1463 | 1249 |
| FrontierMath (Tiers 1-3) | 86% | — |
| FrontierMath Tier 4 | 70.7% | — |
| OTIS Mock AIME 2024-2025 | 99.7% | — |
| ProofBench | 74% | — |
Knowledge GPT-5.6 Terra leads
GPT-5.6 Terra: 61.3 (#27), Magistral Medium: 32.9 (#199)
| Benchmark | GPT-5.6 Terra | Magistral Medium |
|---|---|---|
| LMArena Expert | 1492 | 1222 |
| GPQA Diamond | 93.3% | — |
| SimpleQA Verified | 43.2% | — |
Multimodal Not comparable
GPT-5.6 Terra: 47.5 (#10), Magistral Medium: —
| Benchmark | GPT-5.6 Terra | Magistral Medium |
|---|---|---|
| LMArena Vision | 1271 | — |
| Blueprint-Bench 2 | 30.8% | — |
| Furniture Assembly | 54.2% | — |
| LMArena Document | 1472 | — |
Multilingual GPT-5.6 Terra leads
GPT-5.6 Terra: 54.5 (#42), Magistral Medium: 39.8 (#219)
| Benchmark | GPT-5.6 Terra | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1439 | 1232 |
| LMArena Chinese | 1514 | 1225 |
| LMArena French | 1476 | 1268 |
| LMArena German | 1462 | 1248 |
| LMArena Japanese | 1446 | 1176 |
| LMArena Korean | 1420 | 1125 |
| LMArena Russian | 1450 | 1224 |
| LMArena Spanish | 1455 | 1269 |
Instruction Following GPT-5.6 Terra leads
GPT-5.6 Terra: 76.6 (#38), Magistral Medium: 66.2 (#207)
| Benchmark | GPT-5.6 Terra | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1453 | 1254 |
Long Context GPT-5.6 Terra leads
GPT-5.6 Terra: 44.4 (#64), Magistral Medium: 39.3 (#178)
| Benchmark | GPT-5.6 Terra | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1452 | 1295 |
Writing & Preference GPT-5.6 Terra leads
GPT-5.6 Terra: 70.4 (#21), Magistral Medium: 46.5 (#214)
| Benchmark | GPT-5.6 Terra | Magistral Medium |
|---|---|---|
| LMArena Text | 1446 | 1255 |
| LMArena Creative Writing | 1411 | 1245 |
| LMArena Multi-Turn | 1451 | 1275 |
| EQ-Bench Creative Writing | 1855 | — |
| EQ-Bench 4 | 1234 | — |
Frequently asked questions
Is GPT-5.6 Terra better than Magistral Medium?
GPT-5.6 Terra is the stronger model overall, scoring 59.1 to 34.8 on the Noometry Index. Magistral Medium costs 1.6× 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 Magistral Medium?
Magistral Medium is cheaper. It lists at $2 per million input tokens and $5 per million output tokens; GPT-5.6 Terra lists at $2 and $12.
Is GPT-5.6 Terra or Magistral Medium better for coding?
GPT-5.6 Terra scores higher on coding benchmarks: 57.1 versus 38.6 in the Noometry coding category.
Which has the bigger context window?
GPT-5.6 Terra does, with 1.05M tokens against 128K.
How many benchmarks do GPT-5.6 Terra and Magistral Medium share?
22 benchmarks have published results for both models. GPT-5.6 Terra has 52 scored results on Noometry and Magistral Medium has 22.