# GPT-5.6 Terra vs Mistral Medium

> GPT-5.6 Terra is the stronger model overall, scoring 59.1 to 36.0 on the Noometry Index. Mistral Medium costs 1.5× less per token, which makes it the better buy when GPT-5.6 Terra's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-5-6-terra-vs-mistral-medium
- Last updated: 2026-10-10
- Shared benchmarks: 30

## Summary

- They share 30 benchmarks with published results for both. GPT-5.6 Terra scores higher in 10 categories and Mistral Medium in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Terra leads 81.5 to 27.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 99.7% for GPT-5.6 Terra and 32.2% for Mistral Medium.
- Mistral Medium is cheaper at $1.50 / $7.50 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 Medium has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.6 Terra | Mistral Medium |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 59.1 | 36.0 |
| Rank | 15 | 211 |
| Context | 1.05M | 262K |
| Input $/M | $2 | $1.50 |
| Output $/M | $12 | $7.50 |
| Weights | Proprietary | Open |

## Coding

- GPT-5.6 Terra: 57.1 (#16)
- Mistral Medium: 33.8 (#241)

| Benchmark | GPT-5.6 Terra | Mistral Medium |
|---|---|---|
| FrontierCode | 41.3% | 8% |
| SciCode | 55% | 40.2% |
| WeirdML | 78.3% | 43.7% |
| LMArena Coding | 1484 | 1434 |
| ALE-Bench | 1,951 | 763.98 |
| DeepSWE | 69.6% | — |
| CursorBench | 41.3% | — |
| LMArena WebDev | 1520 | — |

## Agentic & Tool Use

- GPT-5.6 Terra: 40.2 (#23)
- Mistral Medium: 28.1 (#84)

| Benchmark | GPT-5.6 Terra | Mistral Medium |
|---|---|---|
| APEX-Agents | 58.2% | — |
| Berkeley Function Calling Leaderboard | — | 37.7% |
| BALROG | 53.2% | — |
| GDP.pdf | 24.7% | — |
| Vending-Bench 2 | 7,343 | — |

## Reasoning

- GPT-5.6 Terra: 60.6 (#19)
- Mistral Medium: 23.3 (#165)

| Benchmark | GPT-5.6 Terra | Mistral Medium |
|---|---|---|
| Kagi LLM Benchmark | 51.3% | 50% |
| CritPt | 30% | 0% |
| LMArena Hard Prompts | 1467 | 1426 |
| DTBench | 93.3% | 75.5% |
| LMCA | 55% | 26.1% |
| Surface Evolver Bench | 83.8% | 26.9% |
| ARC-AGI-2 | 83.9% | — |
| SimpleBench | 48.9% | — |
| NYT Connections (extended) | 78.4% | — |
| ARC-AGI-1 | 96.5% | — |
| Chess Puzzles | 54% | — |
| Mystery Game Puzzles | 35% | — |
| Epoch Capabilities Index | 159.31 | — |

## Math

- GPT-5.6 Terra: 81.5 (#10)
- Mistral Medium: 27.2 (#238)

| Benchmark | GPT-5.6 Terra | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 99.7% | 32.2% |
| ProofBench | 74% | 9% |
| LMArena Math | 1463 | 1409 |
| FrontierMath (Tiers 1-3) | 86% | — |
| FrontierMath Tier 4 | 70.7% | — |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |

## Knowledge

- GPT-5.6 Terra: 61.3 (#27)
- Mistral Medium: 24.9 (#260)

| Benchmark | GPT-5.6 Terra | Mistral Medium |
|---|---|---|
| GPQA Diamond | 93.3% | 59.5% |
| LMArena Expert | 1492 | 1408 |
| Humanity's Last Exam | — | 4.5% |
| SimpleQA Verified | 43.2% | — |
| Vectara Hallucination Rate | — | 22.7% |

## Multimodal

- GPT-5.6 Terra: 47.5 (#10)
- Mistral Medium: 34.6 (#82)

| Benchmark | GPT-5.6 Terra | Mistral Medium |
|---|---|---|
| LMArena Vision | 1271 | 1172 |
| Blueprint-Bench 2 | 30.8% | — |
| Furniture Assembly | 54.2% | — |
| LMArena Document | 1472 | — |

## Multilingual

- GPT-5.6 Terra: 54.5 (#42)
- Mistral Medium: 52.3 (#86)

| Benchmark | GPT-5.6 Terra | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1439 | 1408 |
| LMArena Chinese | 1514 | 1448 |
| LMArena French | 1476 | 1460 |
| LMArena German | 1462 | 1433 |
| LMArena Japanese | 1446 | 1378 |
| LMArena Korean | 1420 | 1382 |
| LMArena Russian | 1450 | 1411 |
| LMArena Spanish | 1455 | 1433 |

## Instruction Following

- GPT-5.6 Terra: 76.6 (#38)
- Mistral Medium: 73.9 (#111)

| Benchmark | GPT-5.6 Terra | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1453 | 1398 |

## Long Context

- GPT-5.6 Terra: 44.4 (#64)
- Mistral Medium: 42.9 (#108)

| Benchmark | GPT-5.6 Terra | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1452 | 1406 |

## Writing & Preference

- GPT-5.6 Terra: 70.4 (#21)
- Mistral Medium: 60.2 (#97)

| Benchmark | GPT-5.6 Terra | Mistral Medium |
|---|---|---|
| LMArena Text | 1446 | 1424 |
| LMArena Creative Writing | 1411 | 1391 |
| LMArena Multi-Turn | 1451 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
| EQ-Bench Creative Writing | 1855 | — |
| EQ-Bench 4 | 1234 | — |

## FAQ

### Is GPT-5.6 Terra better than Mistral Medium?

GPT-5.6 Terra is the stronger model overall, scoring 59.1 to 36.0 on the Noometry Index. Mistral Medium costs 1.5× 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 Medium?

Mistral Medium is cheaper. It lists at $1.50 per million input tokens and $7.50 per million output tokens; GPT-5.6 Terra lists at $2 and $12.

### Is GPT-5.6 Terra or Mistral Medium better for coding?

GPT-5.6 Terra scores higher on coding benchmarks: 57.1 versus 33.8 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 Medium share?

30 benchmarks have published results for both models. GPT-5.6 Terra has 52 scored results on Noometry and Mistral Medium has 36.