GPT-6.1 Terra vs Mistral Large 4
GPT-6.1 Terra leads Mistral Large 4 on coding, 77.4 to 56.4 on the Vibe Coding Index, at about the same output price ($5.00 vs $4.18 per million). Updated October 29, 2026; 32 benchmarks have a result for both.
GPT-6.1 Terra or Mistral Large 4: which to pick
Pick GPT-6.1 Terra for coding: it scores 77.4 on the Vibe Coding Index against 56.4 for Mistral Large 4, though on 4 benchmarks against 5.
Pick Mistral Large 4 for output tokens 1.2x cheaper ($4.18 vs $5.00 per million) and work measured by Tax Agent Bench (Vals AI) or Legal Research Bench (Vals AI), where it leads.
- Shared results
- 32
- GPT-6.1 Terra only
- 4
- Mistral Large 4 only
- 53
- 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-6.1 Terra
GPT-6.1 Terra scores 77.4 against 56.4.
4 and 5 benchmarks behind the scores
Intelligence
AA Intelligence Index
GPT-6.1 Terra
GPT-6.1 Terra leads, 51.0 against 25.3.
Same board, both measured
Web design
Design Arena: websites
GPT-6.1 Terra
GPT-6.1 Terra leads, 1283 against 1256.
Same board, both measured
General
Vals Index
No call
Only GPT-6.1 Terra has a Vals Index result, 60.5%.
Directional only
Long documents
Listed context window
GPT-6.1 Terra
GPT-6.1 Terra takes 1.05M tokens against 1.05M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Mistral Large 4
GPT-6.1 Terra $0.0035, Mistral Large 4 $0.0034 per turn.
List prices
At a glance
- Coding index
- GPT-6.1 Terra 77.4 from 4 benchmarks, Mistral Large 4 56.4 from 5 benchmarks.
- Widest category
- Knowledge, 37.3 points apart on average over 1 shared benchmark.
- Widest single gap
- LiveBench browser: GPT-6.1 Terra 93.1% against Mistral Large 4 0.6%, 92.5 points apart on a 0 to 100 scale.
- Output price
- GPT-6.1 Terra $5.00 against Mistral Large 4 $4.18 per million output tokens, 1.2x apart.
- Context window
- GPT-6.1 Terra takes 1.05M tokens, Mistral Large 4 1.05M.
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-6.1 Terra | Bars | Mistral Large 4 | Ties |
|---|---|---|---|---|
| Coding | 8 | 0 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 4 | 3 | ||
| Reasoning | 4 | 0 | ||
| Math | 3 | 0 | ||
| Knowledge | 1 | 0 | ||
| Web design | 5 | 0 | ||
| General | 3 | 0 | ||
| All shared boards | 29 | 3 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index80
| Benchmark | GPT-6.1 Terra | Mistral Large 4 | Leader |
|---|---|---|---|
| LiveBench coding | 94.3% | 60.0% | GPT-6.1 Terra |
| LMArena WebDev | 1673 | 1544 | GPT-6.1 Terra |
| Terminal-Bench 4 (Vals AI) | 49.5% | 27.8% | GPT-6.1 Terra |
| Vibe Code Bench (Vals AI) | 84.0% | 78.4% | GPT-6.1 Terra |
| Code migration (Vals AI) | Not measured | 30.6% | Only Mistral Large 4 measured |
| IOI (Vals AI) | Not measured | 45.3% | Only Mistral Large 4 measured |
| SWE-bench Multimodal (Vals AI) | Not measured | 33.1% | Only Mistral Large 4 measured |
| Vibe Code Bench 1-100 (Vals AI) | Not measured | 14.3% | Only Mistral Large 4 measured |
| SciCode | 55.1% | 54.2% | GPT-6.1 Terra |
| FrontierCode | Not measured | 39.4% | Only Mistral Large 4 measured |
| ALE-Bench | 2608.8 | 1213.2 | GPT-6.1 Terra |
| LMArena Text: coding | Not measured | 1478 | Only Mistral Large 4 measured |
| LMArena Text: software and IT | Not measured | 1467 | Only Mistral Large 4 measured |
| LMArena WebDev: React | 1657 | 1559 | GPT-6.1 Terra |
| LMArena WebDev: HTML | 1719 | 1495 | GPT-6.1 Terra |
| Neither model has a result on the other 28 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GPT-6.1 Terra | Mistral Large 4 | Leader |
|---|---|---|---|
| AA Intelligence Index | 51.0 | 25.3 | GPT-6.1 Terra |
| Epoch Capabilities Index | Not measured | 150.0 | Only Mistral Large 4 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index43
| Benchmark | GPT-6.1 Terra | Mistral Large 4 | Leader |
|---|---|---|---|
| LiveBench research | 73.9% | 28.1% | GPT-6.1 Terra |
| LiveBench browser | 93.1% | 0.6% | GPT-6.1 Terra |
| LiveBench long agentic | 48.6% | 8.8% | GPT-6.1 Terra |
| Finance Agent (Vals AI) | Not measured | 54.7% | Only Mistral Large 4 measured |
| Tax Agent Bench (Vals AI) | 15.2% | 30.4% | Mistral Large 4 |
| Legal Research Bench (Vals AI) | 26.0% | 31.7% | Mistral Large 4 |
| Harvey's Legal Agent Benchmark (Vals AI) | 1.7% | 17.5% | Mistral Large 4 |
| Excel Modeling Benchmark (Vals AI) | Not measured | 56.2% | Only Mistral Large 4 measured |
| BioMysteryBench (Vals AI) | Not measured | 67.0% | Only Mistral Large 4 measured |
| APEX-Agents | 68.3% | 51.6% | GPT-6.1 Terra |
| Neither model has a result on the other 32 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | GPT-6.1 Terra | Mistral Large 4 | Leader |
|---|---|---|---|
| LiveBench reasoning | 88.7% | 83.9% | GPT-6.1 Terra |
| MysteryMechanism (Vals AI) | Not measured | 12.2% | Only Mistral Large 4 measured |
| Humanity's Last Exam (Artificial Analysis run) | 46.2% | 35.0% | GPT-6.1 Terra |
| GPQA Diamond (Epoch AI run) | 94.3% | 88.1% | GPT-6.1 Terra |
| Chess puzzles | Not measured | 33.0% | Only Mistral Large 4 measured |
| Mystery game puzzles | 74.0% | 17.0% | GPT-6.1 Terra |
| EBR-bench | 78.1% | Not measured | Only GPT-6.1 Terra measured |
| LMArena Text: hard prompts | Not measured | 1444 | Only Mistral Large 4 measured |
| LMArena Text: expert | Not measured | 1447 | Only Mistral Large 4 measured |
| LMArena Text: hard prompts in English | Not measured | 1441 | Only Mistral Large 4 measured |
| LMArena Vision: diagrams | Not measured | 1288 | Only Mistral Large 4 measured |
| Humanity's Last Exam (Scale run) | 35.7% | Not measured | Only GPT-6.1 Terra measured |
| Neither model has a result on the other 11 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | GPT-6.1 Terra | Mistral Large 4 | Leader |
|---|---|---|---|
| OTIS Mock AIME | 100.0% | 98.3% | GPT-6.1 Terra |
| FrontierMath, tiers 1 to 3 | 90.9% | 58.6% | GPT-6.1 Terra |
| FrontierMath, tier 4 | 92.7% | 26.8% | GPT-6.1 Terra |
| ProofBench | Not measured | 10.0% | Only Mistral Large 4 measured |
| LMArena Text: math | Not measured | 1468 | Only Mistral Large 4 measured |
| LMArena Text: mathematical work | Not measured | 1468 | Only Mistral Large 4 measured |
| MathArena | Not measured | 26.2% | Only Mistral Large 4 measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GPT-6.1 Terra | Mistral Large 4 | Leader |
|---|---|---|---|
| MedCode (Vals AI) | Not measured | 40.7% | Only Mistral Large 4 measured |
| SimpleQA Verified | 57.3% | 20.0% | GPT-6.1 Terra |
| LMArena Text: science | Not measured | 1443 | Only Mistral Large 4 measured |
| LMArena Text: medicine and healthcare | Not measured | 1428 | Only Mistral Large 4 measured |
| LMArena Text: legal and government | Not measured | 1428 | Only Mistral Large 4 measured |
| LMArena Text: business and finance | Not measured | 1439 | Only Mistral Large 4 measured |
| Neither model has a result on the other 14 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | GPT-6.1 Terra | Mistral Large 4 | Leader |
|---|---|---|---|
| Design Arena: websites | 1283 | 1256 | GPT-6.1 Terra |
| Design Arena: UI components | 1277 | 1270 | GPT-6.1 Terra |
| Design Arena: game dev | 1348 | 1225 | GPT-6.1 Terra |
| Design Arena: data viz | Not measured | 1274 | Only Mistral Large 4 measured |
| Design Arena: 3D | Not measured | 1248 | Only Mistral Large 4 measured |
| Design Arena: all code categories | 1295 | 1258 | GPT-6.1 Terra |
| Design Arena: SVG | Not measured | 1230 | Only Mistral Large 4 measured |
| Design Arena: ASCII art | Not measured | 1207 | Only Mistral Large 4 measured |
| LiveBench design | 82.3% | 65.6% | GPT-6.1 Terra |
GeneralLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | GPT-6.1 Terra | Mistral Large 4 | Leader |
|---|---|---|---|
| Vals Index | 60.5% | Not measured | Only GPT-6.1 Terra measured |
| LiveBench data analysis | 82.3% | 76.5% | GPT-6.1 Terra |
| MedScribe (Vals AI) | Not measured | 80.4% | Only Mistral Large 4 measured |
| Long context reasoning (AA-LCR) | 82.7% | 81.3% | GPT-6.1 Terra |
| DTBench | Not measured | 88.2% | Only Mistral Large 4 measured |
| LMCA | Not measured | 35.8% | Only Mistral Large 4 measured |
| Surface Evolver Bench | Not measured | 28.1% | Only Mistral Large 4 measured |
| Furniture assembly | 79.2% | 20.8% | GPT-6.1 Terra |
| LMArena Text | Not measured | 1430 | Only Mistral Large 4 measured |
| LMArena Text: instruction following | Not measured | 1419 | Only Mistral Large 4 measured |
| LMArena Text: creative writing | Not measured | 1361 | Only Mistral Large 4 measured |
| LMArena Vision | Not measured | 1272 | Only Mistral Large 4 measured |
| LMArena Text: English | Not measured | 1432 | Only Mistral Large 4 measured |
| LMArena Text: non-English | Not measured | 1420 | Only Mistral Large 4 measured |
| LMArena Text: Chinese | Not measured | 1492 | Only Mistral Large 4 measured |
| LMArena Text: German | Not measured | 1409 | Only Mistral Large 4 measured |
| LMArena Text: Japanese | Not measured | 1413 | Only Mistral Large 4 measured |
| LMArena Text: Korean | Not measured | 1375 | Only Mistral Large 4 measured |
| LMArena Text: French | Not measured | 1489 | Only Mistral Large 4 measured |
| LMArena Text: Spanish | Not measured | 1470 | Only Mistral Large 4 measured |
| LMArena Text: Russian | Not measured | 1414 | Only Mistral Large 4 measured |
| LMArena Text: multi-turn | Not measured | 1437 | Only Mistral Large 4 measured |
| LMArena Text: longer queries | Not measured | 1428 | Only Mistral Large 4 measured |
| LMArena Text: writing and language | Not measured | 1385 | Only Mistral Large 4 measured |
| LMArena Text: entertainment and media | Not measured | 1376 | Only Mistral Large 4 measured |
| LMArena Vision: English | Not measured | 1283 | Only Mistral Large 4 measured |
| LMArena Vision: reading text | Not measured | 1284 | Only Mistral Large 4 measured |
| MultiChallenge | 74.2% | Not measured | Only GPT-6.1 Terra measured |
| Neither model has a result on the other 20 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-6.1 Terra | Mistral Large 4 | 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 Large 4 costs less
Repository review
50K input + 3K output tokens
GPT-6.1 Terra costs less
Agent loop
200K input + 10K output tokens
GPT-6.1 Terra 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-6.1 Terra | Mistral Large 4 |
|---|---|---|
| Maker | OpenAI | Mistral AI |
| Weights | No public weights listed | No public weights listed |
| Released | October 26, 2026 | October 6, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $1.00 | $1.36 |
| Output $/Mtok | $5.00 | $4.18 |
| Coding index | 77.4 | 56.4 |
| Independent measurements behind it | 4 | 5 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-6.1 Terra better than Mistral Large 4 for coding?
Pick GPT-6.1 Terra for coding: it scores 77.4 on the Vibe Coding Index against 56.4 for Mistral Large 4, though on 4 benchmarks against 5. Pick Mistral Large 4 for output tokens 1.2x cheaper ($4.18 vs $5.00 per million) and work measured by Tax Agent Bench (Vals AI) or Legal Research Bench (Vals AI), where it leads.
Which is cheaper, GPT-6.1 Terra or Mistral Large 4?
GPT-6.1 Terra costs $1.00 per million input tokens and $5.00 per million output tokens; Mistral Large 4 costs $1.36 and $4.18. Cost per solved task is known for neither of them.
Which has the bigger context window, GPT-6.1 Terra or Mistral Large 4?
GPT-6.1 Terra, with 1.05M tokens against 1.05M.
How many benchmarks is the GPT-6.1 Terra vs Mistral Large 4 comparison based on?
32 benchmarks have a result for both models as of October 29, 2026. GPT-6.1 Terra's coding index rests on 4 independent benchmarks and Mistral Large 4's on 5. Where only one model has a result, the page says so instead of naming a winner.