GPT-5.6 Terra vs Mistral Medium 3.5
GPT-5.6 Terra leads Mistral Medium 3.5 on coding, 63.9 to 25.5 on the Vibe Coding Index, and Mistral Medium 3.5 costs 1.6x less per output token ($7.50 vs $12.00 per million). Updated October 22, 2026; 80 benchmarks have a result for both.
GPT-5.6 Terra or Mistral Medium 3.5: which to pick
Pick GPT-5.6 Terra for coding: it scores 63.9 on the Vibe Coding Index against 25.5 for Mistral Medium 3.5.
Pick Mistral Medium 3.5 for output tokens 1.6x cheaper ($7.50 vs $12.00 per million) and work measured by τ²-Bench Telecom, where it leads.
- Shared results
- 80
- GPT-5.6 Terra only
- 47
- Mistral Medium 3.5 only
- 1
- Like-for-like categories
- 8 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
GPT-5.6 Terra
GPT-5.6 Terra scores 63.9 against 25.5.
6 and 3 benchmarks behind the scores
Intelligence
AA Intelligence Index
GPT-5.6 Terra
GPT-5.6 Terra leads, 42.1 against 14.2.
Same board, both measured
Agentic work
AA Agentic Index
GPT-5.6 Terra
GPT-5.6 Terra leads, 43.2 against 7.0.
Same board, both measured
Reasoning
GPQA Diamond
GPT-5.6 Terra
GPT-5.6 Terra leads, 90.9% against 34.9%.
Same board, both measured
Knowledge
MMLU Pro
GPT-5.6 Terra
GPT-5.6 Terra leads, 86.7% against 75.3%.
Same board, both measured
Web design
Design Arena: websites
GPT-5.6 Terra
GPT-5.6 Terra leads, 1268 against 1142.
Same board, both measured
Long documents
Listed context window
GPT-5.6 Terra
GPT-5.6 Terra takes 1.05M tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Mistral Medium 3.5
GPT-5.6 Terra $0.0080, Mistral Medium 3.5 $0.0053 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
GPT-5.6 Terra
GPT-5.6 Terra $0.42, Mistral Medium 3.5 $6.02.
Published attempt cost and pass rate
At a glance
- Coding index
- GPT-5.6 Terra 63.9 from 6 benchmarks, Mistral Medium 3.5 25.5 from 3 benchmarks.
- Widest category
- Coding, 32.3 points apart on average over 13 shared benchmarks.
- Widest single gap
- Vibe Code Bench (Vals AI): GPT-5.6 Terra 74.6% against Mistral Medium 3.5 2.9%, 71.7 points apart on a 0 to 100 scale.
- Output price
- GPT-5.6 Terra $12.00 against Mistral Medium 3.5 $7.50 per million output tokens, 1.6x apart.
- Context window
- GPT-5.6 Terra takes 1.05M tokens, Mistral Medium 3.5 262K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | GPT-5.6 Terra | Bars | Mistral Medium 3.5 | Ties |
|---|---|---|---|---|
| Coding | 13 | 0 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 5 | 1 | ||
| Reasoning | 9 | 0 | ||
| Math | 3 | 0 | ||
| Knowledge | 9 | 0 | ||
| Web design | 8 | 0 | ||
| General | 30 | 0 | ||
| All shared boards | 79 | 1 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index130
| Benchmark | GPT-5.6 Terra | Mistral Medium 3.5 | Leader |
|---|---|---|---|
| LiveBench coding | 86.2% | Not measured | Only GPT-5.6 Terra measured |
| LMArena WebDev | 1522 | 1264 | GPT-5.6 Terra |
| AA Coding Index | 76.7 | 46.9 | GPT-5.6 Terra |
| LiveCodeBench (Vals AI) | 85.9% | Not measured | Only GPT-5.6 Terra measured |
| SWE-bench Verified (Vals AI) | 95.4% | 66.4% | GPT-5.6 Terra |
| Terminal-Bench 4 (Vals AI) | 22.7% | Not measured | Only GPT-5.6 Terra measured |
| Vibe Code Bench (Vals AI) | 74.6% | 2.9% | GPT-5.6 Terra |
| Code migration (Vals AI) | 47.8% | 5.1% | GPT-5.6 Terra |
| ProgramBench (Vals AI) | 0.5% | Not measured | Only GPT-5.6 Terra measured |
| IOI (Vals AI) | 87.6% | Not measured | Only GPT-5.6 Terra measured |
| Terminal-Bench 2.1 (Vals AI) | 77.5% | 39.0% | GPT-5.6 Terra |
| Vibe Code Bench 1-100 (Vals AI) | 14.8% | Not measured | Only GPT-5.6 Terra measured |
| SkillsBench (Vals AI) | 58.9% | Not measured | Only GPT-5.6 Terra measured |
| CyberBench (Vals AI) | 72.1% | Not measured | Only GPT-5.6 Terra measured |
| SciCode | 55.0% | 40.2% | GPT-5.6 Terra |
| Terminal-Bench Hard (Artificial Analysis run) | 62.9% | 33.3% | GPT-5.6 Terra |
| FrontierCode | 41.3% | Not measured | Only GPT-5.6 Terra measured |
| WeirdML | 78.3% | Not measured | Only GPT-5.6 Terra measured |
| ALE-Bench | 1951.4 | 764.0 | GPT-5.6 Terra |
| LMArena Text: coding | 1485 | 1460 | GPT-5.6 Terra |
| LMArena Text: software and IT | 1482 | 1458 | GPT-5.6 Terra |
| LMArena WebDev: React | 1513 | 1254 | GPT-5.6 Terra |
| LMArena WebDev: HTML | 1526 | 1308 | GPT-5.6 Terra |
| LMArena WebDev: from an image | 1541 | Not measured | Only GPT-5.6 Terra measured |
| SciCode | 10.8% | Not measured | Only GPT-5.6 Terra measured |
| Neither model has a result on the other 14 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | GPT-5.6 Terra | Mistral Medium 3.5 | Leader |
|---|---|---|---|
| AA Intelligence Index | 42.1 | 14.2 | GPT-5.6 Terra |
| Epoch Capabilities Index | 160.1 | 141.4 | GPT-5.6 Terra |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index51
| Benchmark | GPT-5.6 Terra | Mistral Medium 3.5 | Leader |
|---|---|---|---|
| AA Agentic Index | 43.2 | 7.0 | GPT-5.6 Terra |
| Design Arena: agents building web apps | 1120 | Not measured | Only GPT-5.6 Terra measured |
| Design Arena: agents building full-stack apps | 1061 | Not measured | Only GPT-5.6 Terra measured |
| Design Arena: agents building mobile apps | 1111 | Not measured | Only GPT-5.6 Terra measured |
| Design Arena: agents building Android apps | 1062 | Not measured | Only GPT-5.6 Terra measured |
| Design Arena: agents building games | 1083 | Not measured | Only GPT-5.6 Terra measured |
| Design Arena: HTML slides | 1058 | Not measured | Only GPT-5.6 Terra measured |
| Design Arena: PowerPoint slides | 1105 | Not measured | Only GPT-5.6 Terra measured |
| LiveBench research | 60.4% | Not measured | Only GPT-5.6 Terra measured |
| LiveBench browser | 84.0% | Not measured | Only GPT-5.6 Terra measured |
| LiveBench long agentic | 48.4% | Not measured | Only GPT-5.6 Terra measured |
| SREBench (Vals AI) | 9.5% | Not measured | Only GPT-5.6 Terra measured |
| Finance Agent (Vals AI) | 54.4% | 32.1% | GPT-5.6 Terra |
| Tax Agent Bench (Vals AI) | 30.0% | 4.5% | GPT-5.6 Terra |
| Legal Research Bench (Vals AI) | 41.4% | 9.1% | GPT-5.6 Terra |
| Excel Modeling Benchmark (Vals AI) | 66.2% | 11.2% | GPT-5.6 Terra |
| Terminal-Bench-Science (Vals AI) | 10.0% | Not measured | Only GPT-5.6 Terra measured |
| τ²-Bench Telecom | 86.3% | 94.2% | Mistral Medium 3.5 |
| APEX-Agents | 58.2% | Not measured | Only GPT-5.6 Terra measured |
| BALROG | 53.2% | Not measured | Only GPT-5.6 Terra measured |
| Vending-Bench 2 | $7,343 | Not measured | Only GPT-5.6 Terra measured |
| Neither model has a result on the other 20 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index90
| Benchmark | GPT-5.6 Terra | Mistral Medium 3.5 | Leader |
|---|---|---|---|
| GPQA Diamond | 90.9% | 34.9% | GPT-5.6 Terra |
| LiveBench reasoning | 90.6% | Not measured | Only GPT-5.6 Terra measured |
| MMMU Pro (Vals AI) | 86.5% | Not measured | Only GPT-5.6 Terra measured |
| GPQA Diamond (Artificial Analysis run) | 92.5% | 74.8% | GPT-5.6 Terra |
| Humanity's Last Exam (Artificial Analysis run) | 42.9% | 13.8% | GPT-5.6 Terra |
| GPQA Diamond (Epoch AI run) | 93.3% | Not measured | Only GPT-5.6 Terra measured |
| ARC-AGI | 96.5% | Not measured | Only GPT-5.6 Terra measured |
| ARC-AGI-2 | 83.9% | Not measured | Only GPT-5.6 Terra measured |
| SimpleBench | 48.9% | Not measured | Only GPT-5.6 Terra measured |
| Chess puzzles | 47.0% | Not measured | Only GPT-5.6 Terra measured |
| Mystery game puzzles | 35.0% | Not measured | Only GPT-5.6 Terra measured |
| LMArena Text: hard prompts | 1469 | 1436 | GPT-5.6 Terra |
| LMArena Text: expert | 1496 | 1432 | GPT-5.6 Terra |
| LMArena Text: hard prompts in English | 1465 | 1445 | GPT-5.6 Terra |
| LMArena Vision: diagrams | 1295 | 1254 | GPT-5.6 Terra |
| LMArena Vision: homework | 1312 | 1230 | GPT-5.6 Terra |
| Kagi LLM Benchmark | 51.3% | 41.4% | GPT-5.6 Terra |
| Neither model has a result on the other 5 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | GPT-5.6 Terra | Mistral Medium 3.5 | Leader |
|---|---|---|---|
| OTIS Mock AIME | 99.7% | Not measured | Only GPT-5.6 Terra measured |
| FrontierMath, tiers 1 to 3 | 86.0% | Not measured | Only GPT-5.6 Terra measured |
| FrontierMath, tier 4 | 70.7% | Not measured | Only GPT-5.6 Terra measured |
| ProofBench | 74.0% | 9.0% | GPT-5.6 Terra |
| LMArena Text: math | 1465 | 1431 | GPT-5.6 Terra |
| LMArena Text: mathematical work | 1478 | 1440 | GPT-5.6 Terra |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index90
| Benchmark | GPT-5.6 Terra | Mistral Medium 3.5 | Leader |
|---|---|---|---|
| MMLU Pro | 86.7% | 75.3% | GPT-5.6 Terra |
| LegalBench (Vals AI) | 85.1% | Not measured | Only GPT-5.6 Terra measured |
| CaseLaw (Vals AI) | Not measured | 44.2% | Only Mistral Medium 3.5 measured |
| CorpFin (Vals AI) | 65.3% | 58.8% | GPT-5.6 Terra |
| TaxEval (Vals AI) | 76.2% | 68.0% | GPT-5.6 Terra |
| MortgageTax (Vals AI) | 67.3% | 28.9% | GPT-5.6 Terra |
| MedCode (Vals AI) | 43.4% | 33.8% | GPT-5.6 Terra |
| SimpleQA Verified | 43.2% | Not measured | Only GPT-5.6 Terra measured |
| LMArena Text: science | 1452 | 1428 | GPT-5.6 Terra |
| LMArena Text: medicine and healthcare | 1430 | 1409 | GPT-5.6 Terra |
| LMArena Text: legal and government | 1461 | 1437 | GPT-5.6 Terra |
| LMArena Text: business and finance | 1448 | 1426 | GPT-5.6 Terra |
| FACTS Benchmark Suite | 52.0% | Not measured | Only GPT-5.6 Terra measured |
| Neither model has a result on the other 5 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index80
| Benchmark | GPT-5.6 Terra | Mistral Medium 3.5 | Leader |
|---|---|---|---|
| Design Arena: websites | 1268 | 1142 | GPT-5.6 Terra |
| Design Arena: UI components | 1256 | 1076 | GPT-5.6 Terra |
| Design Arena: game dev | 1229 | 1079 | GPT-5.6 Terra |
| Design Arena: data viz | 1240 | 1120 | GPT-5.6 Terra |
| Design Arena: 3D | 1134 | 1060 | GPT-5.6 Terra |
| Design Arena: all code categories | 1241 | 1121 | GPT-5.6 Terra |
| Design Arena: SVG | 1219 | 949 | GPT-5.6 Terra |
| Design Arena: ASCII art | 1177 | 1062 | GPT-5.6 Terra |
| LiveBench design | 76.0% | Not measured | Only GPT-5.6 Terra measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index300
| Benchmark | GPT-5.6 Terra | Mistral Medium 3.5 | Leader |
|---|---|---|---|
| LiveBench data analysis | 79.3% | Not measured | Only GPT-5.6 Terra measured |
| Public Benefits Bench (Vals AI) | 62.4% | Not measured | Only GPT-5.6 Terra measured |
| SAGE (Vals AI) | 47.0% | 37.6% | GPT-5.6 Terra |
| MedScribe (Vals AI) | 82.9% | 67.7% | GPT-5.6 Terra |
| Vals Multimodal Index | 65.1% | 34.8% | GPT-5.6 Terra |
| IFBench | 71.2% | 68.8% | GPT-5.6 Terra |
| Long context reasoning (AA-LCR) | 83.0% | 69.3% | GPT-5.6 Terra |
| DTBench | 93.3% | 75.5% | GPT-5.6 Terra |
| LMCA | 54.9% | 26.1% | GPT-5.6 Terra |
| Surface Evolver Bench | 83.8% | 26.9% | GPT-5.6 Terra |
| Furniture assembly | 54.2% | Not measured | Only GPT-5.6 Terra measured |
| LMArena Text | 1448 | 1421 | GPT-5.6 Terra |
| LMArena Text: instruction following | 1456 | 1415 | GPT-5.6 Terra |
| LMArena Text: creative writing | 1413 | 1374 | GPT-5.6 Terra |
| LMArena Vision | 1271 | 1222 | GPT-5.6 Terra |
| LMArena Text: English | 1449 | 1433 | GPT-5.6 Terra |
| LMArena Text: non-English | 1441 | 1404 | GPT-5.6 Terra |
| LMArena Text: Chinese | 1514 | 1444 | GPT-5.6 Terra |
| LMArena Text: German | 1460 | 1453 | GPT-5.6 Terra |
| LMArena Text: Japanese | 1454 | Not measured | Only GPT-5.6 Terra measured |
| LMArena Text: Korean | 1427 | 1384 | GPT-5.6 Terra |
| LMArena Text: French | 1466 | 1448 | GPT-5.6 Terra |
| LMArena Text: Spanish | 1451 | 1411 | GPT-5.6 Terra |
| LMArena Text: Russian | 1452 | 1395 | GPT-5.6 Terra |
| LMArena Text: Polish | 1446 | 1430 | GPT-5.6 Terra |
| LMArena Text: multi-turn | 1453 | 1423 | GPT-5.6 Terra |
| LMArena Text: longer queries | 1454 | 1415 | GPT-5.6 Terra |
| LMArena Text: writing and language | 1431 | 1384 | GPT-5.6 Terra |
| LMArena Text: entertainment and media | 1418 | 1382 | GPT-5.6 Terra |
| LMArena Vision: English | 1272 | 1240 | GPT-5.6 Terra |
| LMArena Vision: Chinese | 1337 | 1244 | GPT-5.6 Terra |
| LMArena Vision: reading text | 1278 | 1233 | GPT-5.6 Terra |
| LMArena Vision: humor | 1236 | 1216 | GPT-5.6 Terra |
| LMArena Vision: creative writing | 1248 | 1198 | GPT-5.6 Terra |
| LMArena Document | 1472 | Not measured | Only GPT-5.6 Terra measured |
| Neither model has a result on the other 11 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5.6 Terra | Mistral Medium 3.5 | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Mistral Medium 3.5 costs less
Repository review
50K input + 3K output tokens
Mistral Medium 3.5 costs less
Agent loop
200K input + 10K output tokens
Mistral Medium 3.5 costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | OpenAI GPT-5.6 Terra | Mistral Medium 3.5 |
|---|---|---|
| Maker | OpenAI | Mistral AI |
| Weights | No public weights listed | No public weights listed |
| Released | July 9, 2026 | April 30, 2026 |
| Context window | 1.05M | 262K |
| Input $/Mtok | $2.00 | $1.50 |
| Output $/Mtok | $12.00 | $7.50 |
| Coding index | 63.9 | 25.5 |
| Independent measurements behind it | 6 | 3 |
| Cost per solved task | $0.42 | $6.02 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-5.6 Terra better than Mistral Medium 3.5 for coding?
Pick GPT-5.6 Terra for coding: it scores 63.9 on the Vibe Coding Index against 25.5 for Mistral Medium 3.5. Pick Mistral Medium 3.5 for output tokens 1.6x cheaper ($7.50 vs $12.00 per million) and work measured by τ²-Bench Telecom, where it leads.
Which is cheaper, GPT-5.6 Terra or Mistral Medium 3.5?
GPT-5.6 Terra costs $2.00 per million input tokens and $12.00 per million output tokens; Mistral Medium 3.5 costs $1.50 and $7.50. Per solved SWE-bench Verified task, GPT-5.6 Terra costs $0.42 and Mistral Medium 3.5 $6.02.
Which has the bigger context window, GPT-5.6 Terra or Mistral Medium 3.5?
GPT-5.6 Terra, with 1.05M tokens against 262K.
How many benchmarks is the GPT-5.6 Terra vs Mistral Medium 3.5 comparison based on?
80 benchmarks have a result for both models as of October 22, 2026. GPT-5.6 Terra's coding index rests on 6 independent benchmarks and Mistral Medium 3.5's on 3. Where only one model has a result, the page says so instead of naming a winner.