GPT-6 Sol vs Mistral Large 4
GPT-6 Sol leads Mistral Large 4 on coding, 76.0 to 56.4 on the Vibe Coding Index, and Mistral Large 4 costs 2.4x less per output token ($4.18 vs $10.00 per million). Updated October 22, 2026; 77 benchmarks have a result for both.
GPT-6 Sol or Mistral Large 4: which to pick
Pick GPT-6 Sol for coding: it scores 76.0 on the Vibe Coding Index against 56.4 for Mistral Large 4.
Pick Mistral Large 4 for output tokens 2.4x cheaper ($4.18 vs $10.00 per million) and work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.
- Shared results
- 77
- GPT-6 Sol only
- 24
- Mistral Large 4 only
- 4
- 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 Sol
GPT-6 Sol scores 76.0 against 56.4.
5 benchmarks behind each score
Intelligence
AA Intelligence Index
GPT-6 Sol
GPT-6 Sol leads, 47.6 against 38.4.
Same board, both measured
Web design
Design Arena: websites
GPT-6 Sol
GPT-6 Sol leads, 1292 against 1257.
Same board, both measured
Long documents
Listed context window
GPT-6 Sol
GPT-6 Sol takes 1.05M tokens against 1.05M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Mistral Large 4
GPT-6 Sol $0.0070, Mistral Large 4 $0.0034 per turn.
List prices
At a glance
- Coding index
- GPT-6 Sol 76.0 from 5 benchmarks, Mistral Large 4 56.4 from 5 benchmarks.
- Widest category
- Math, 30.9 points apart on average over 6 shared benchmarks.
- Widest single gap
- LiveBench browser: GPT-6 Sol 92.0% against Mistral Large 4 8.0%, 84.0 points apart on a 0 to 100 scale.
- Output price
- GPT-6 Sol $10.00 against Mistral Large 4 $4.18 per million output tokens, 2.4x apart.
- Context window
- GPT-6 Sol 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 Sol | Bars | Mistral Large 4 | Ties |
|---|---|---|---|---|
| Coding | 11 | 2 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 5 | 3 | ||
| Reasoning | 6 | 4 | ||
| Math | 4 | 2 | ||
| Knowledge | 2 | 4 | ||
| Web design | 8 | 1 | ||
| General | 8 | 15 | ||
| All shared boards | 46 | 31 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index112
| Benchmark | GPT-6 Sol | Mistral Large 4 | Leader |
|---|---|---|---|
| LiveBench coding | 93.1% | 60.0% | GPT-6 Sol |
| LMArena WebDev | 1683 | 1543 | GPT-6 Sol |
| Terminal-Bench 4 (Vals AI) | 44.4% | 27.8% | GPT-6 Sol |
| Vibe Code Bench (Vals AI) | 87.8% | 78.4% | GPT-6 Sol |
| Code migration (Vals AI) | 57.2% | 30.6% | GPT-6 Sol |
| ProgramBench (Vals AI) | 2.0% | Not measured | Only GPT-6 Sol measured |
| IOI (Vals AI) | 82.6% | 45.3% | GPT-6 Sol |
| Terminal-Bench 2.1 (Vals AI) | 83.2% | Not measured | Only GPT-6 Sol 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 |
| CyberBench (Vals AI) | 78.0% | Not measured | Only GPT-6 Sol measured |
| SciCode | 57.6% | 54.2% | GPT-6 Sol |
| FrontierCode | 49.3% | 39.4% | GPT-6 Sol |
| ALE-Bench | 2462.0 | 1213.2 | GPT-6 Sol |
| LMArena Text: coding | 1448 | 1478 | Mistral Large 4 |
| LMArena Text: software and IT | 1433 | 1467 | Mistral Large 4 |
| LMArena WebDev: React | 1685 | 1559 | GPT-6 Sol |
| LMArena WebDev: HTML | 1685 | 1487 | GPT-6 Sol |
| LMArena WebDev: from an image | 1660 | Not measured | Only GPT-6 Sol measured |
| Neither model has a result on the other 20 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | GPT-6 Sol | Mistral Large 4 | Leader |
|---|---|---|---|
| AA Intelligence Index | 47.6 | 38.4 | GPT-6 Sol |
| Epoch Capabilities Index | 163.7 | 150.0 | GPT-6 Sol |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index53
| Benchmark | GPT-6 Sol | Mistral Large 4 | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | 1231 | Not measured | Only GPT-6 Sol measured |
| Design Arena: agents building full-stack apps | 1238 | Not measured | Only GPT-6 Sol measured |
| Design Arena: agents building mobile apps | 1217 | Not measured | Only GPT-6 Sol measured |
| LiveBench research | 69.3% | 28.1% | GPT-6 Sol |
| LiveBench browser | 92.0% | 8.0% | GPT-6 Sol |
| LiveBench long agentic | 66.9% | 11.8% | GPT-6 Sol |
| SREBench (Vals AI) | 30.5% | Not measured | Only GPT-6 Sol measured |
| Finance Agent (Vals AI) | 49.0% | 54.7% | Mistral Large 4 |
| Tax Agent Bench (Vals AI) | 15.0% | 30.4% | Mistral Large 4 |
| Legal Research Bench (Vals AI) | 28.9% | 31.7% | Mistral Large 4 |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 17.5% | Only Mistral Large 4 measured |
| Excel Modeling Benchmark (Vals AI) | 71.5% | 56.2% | GPT-6 Sol |
| BioMysteryBench (Vals AI) | 74.8% | 67.0% | GPT-6 Sol |
| Terminal-Bench-Science (Vals AI) | 30.0% | Not measured | Only GPT-6 Sol measured |
| Vals Science Index | 45.0% | Not measured | Only GPT-6 Sol measured |
| APEX-Agents | 54.3% | Not measured | Only GPT-6 Sol measured |
| SpireClimb | 7.5% | Not measured | Only GPT-6 Sol measured |
| Vending-Bench 2 | $14,428 | Not measured | Only GPT-6 Sol measured |
| Neither model has a result on the other 23 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index64
| Benchmark | GPT-6 Sol | Mistral Large 4 | Leader |
|---|---|---|---|
| LiveBench reasoning | 88.7% | 83.9% | GPT-6 Sol |
| MysteryMechanism (Vals AI) | 30.2% | 12.2% | GPT-6 Sol |
| Humanity's Last Exam (Artificial Analysis run) | 47.9% | 35.0% | GPT-6 Sol |
| GPQA Diamond (Epoch AI run) | 94.3% | 88.1% | GPT-6 Sol |
| ARC-AGI | 95.5% | Not measured | Only GPT-6 Sol measured |
| ARC-AGI-2 | 89.6% | Not measured | Only GPT-6 Sol measured |
| Chess puzzles | 56.0% | 33.0% | GPT-6 Sol |
| Mystery game puzzles | 56.0% | 17.0% | GPT-6 Sol |
| EBR-bench | 53.3% | Not measured | Only GPT-6 Sol measured |
| LMArena Text: hard prompts | 1422 | 1444 | Mistral Large 4 |
| LMArena Text: expert | 1437 | 1444 | Mistral Large 4 |
| LMArena Text: hard prompts in English | 1420 | 1442 | Mistral Large 4 |
| LMArena Vision: diagrams | 1270 | 1288 | Mistral Large 4 |
| LMArena Vision: homework | 1286 | Not measured | Only GPT-6 Sol measured |
| Neither model has a result on the other 8 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index42
| Benchmark | GPT-6 Sol | Mistral Large 4 | Leader |
|---|---|---|---|
| OTIS Mock AIME | 100.0% | 98.3% | GPT-6 Sol |
| FrontierMath, tiers 1 to 3 | 89.8% | 58.6% | GPT-6 Sol |
| FrontierMath, tier 4 | 90.0% | 26.8% | GPT-6 Sol |
| ProofBench | 83.0% | 10.0% | GPT-6 Sol |
| LMArena Text: math | 1407 | 1469 | Mistral Large 4 |
| LMArena Text: mathematical work | 1424 | 1462 | Mistral Large 4 |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index24
| Benchmark | GPT-6 Sol | Mistral Large 4 | Leader |
|---|---|---|---|
| MedCode (Vals AI) | 47.1% | 40.7% | GPT-6 Sol |
| SimpleQA Verified | 60.7% | 20.0% | GPT-6 Sol |
| LMArena Text: science | 1389 | 1448 | Mistral Large 4 |
| LMArena Text: medicine and healthcare | 1366 | 1433 | Mistral Large 4 |
| LMArena Text: legal and government | 1396 | 1425 | Mistral Large 4 |
| LMArena Text: business and finance | 1380 | 1439 | Mistral Large 4 |
| FACTS Benchmark Suite | 72.5% | Not measured | Only GPT-6 Sol measured |
| Neither model has a result on the other 11 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index81
| Benchmark | GPT-6 Sol | Mistral Large 4 | Leader |
|---|---|---|---|
| Design Arena: websites | 1292 | 1257 | GPT-6 Sol |
| Design Arena: UI components | 1290 | 1272 | GPT-6 Sol |
| Design Arena: game dev | 1311 | 1225 | GPT-6 Sol |
| Design Arena: data viz | 1269 | 1275 | Mistral Large 4 |
| Design Arena: 3D | 1314 | 1252 | GPT-6 Sol |
| Design Arena: all code categories | 1300 | 1259 | GPT-6 Sol |
| Design Arena: SVG | 1315 | 1232 | GPT-6 Sol |
| Design Arena: ASCII art | 1222 | 1202 | GPT-6 Sol |
| LiveBench design | 82.2% | 65.6% | GPT-6 Sol |
GeneralLike-for-likePublic boards, shown as published, kept out of the index815
| Benchmark | GPT-6 Sol | Mistral Large 4 | Leader |
|---|---|---|---|
| LiveBench data analysis | 81.2% | 76.5% | GPT-6 Sol |
| Public Benefits Bench (Vals AI) | 56.6% | Not measured | Only GPT-6 Sol measured |
| SAGE (Vals AI) | 44.8% | Not measured | Only GPT-6 Sol measured |
| MedScribe (Vals AI) | 82.0% | 80.4% | GPT-6 Sol |
| Long context reasoning (AA-LCR) | 83.7% | 81.3% | GPT-6 Sol |
| DTBench | 97.3% | 88.2% | GPT-6 Sol |
| LMCA | 59.1% | 35.8% | GPT-6 Sol |
| Surface Evolver Bench | Not measured | 28.1% | Only Mistral Large 4 measured |
| Furniture assembly | 58.3% | 20.8% | GPT-6 Sol |
| LMArena Text | 1398 | 1431 | Mistral Large 4 |
| LMArena Text: instruction following | 1413 | 1422 | Mistral Large 4 |
| LMArena Text: creative writing | 1378 | 1363 | GPT-6 Sol |
| LMArena Vision | 1240 | 1272 | Mistral Large 4 |
| LMArena Text: English | 1396 | 1433 | Mistral Large 4 |
| LMArena Text: non-English | 1388 | 1422 | Mistral Large 4 |
| LMArena Text: Chinese | 1412 | 1492 | Mistral Large 4 |
| LMArena Text: German | 1379 | Not measured | Only GPT-6 Sol measured |
| LMArena Text: Japanese | 1377 | 1415 | Mistral Large 4 |
| LMArena Text: Korean | 1336 | Not measured | Only GPT-6 Sol measured |
| LMArena Text: French | 1399 | 1492 | Mistral Large 4 |
| LMArena Text: Spanish | 1387 | 1455 | Mistral Large 4 |
| LMArena Text: Russian | 1402 | 1417 | Mistral Large 4 |
| LMArena Text: Polish | 1372 | Not measured | Only GPT-6 Sol measured |
| LMArena Text: multi-turn | 1414 | 1435 | Mistral Large 4 |
| LMArena Text: longer queries | 1416 | 1428 | Mistral Large 4 |
| LMArena Text: writing and language | 1389 | 1386 | GPT-6 Sol |
| LMArena Text: entertainment and media | 1373 | 1378 | Mistral Large 4 |
| LMArena Vision: English | 1229 | 1283 | Mistral Large 4 |
| LMArena Vision: reading text | 1258 | 1284 | Mistral Large 4 |
| LMArena Vision: creative writing | 1219 | Not measured | Only GPT-6 Sol measured |
| Neither model has a result on the other 16 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-6 Sol | 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
Mistral Large 4 costs less
Agent loop
200K input + 10K output tokens
Mistral Large 4 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 Sol | Mistral Large 4 |
|---|---|---|
| Maker | OpenAI | Mistral AI |
| Weights | No public weights listed | No public weights listed |
| Released | September 22, 2026 | October 6, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $2.00 | $1.36 |
| Output $/Mtok | $10.00 | $4.18 |
| Coding index | 76.0 | 56.4 |
| Independent measurements behind it | 5 | 5 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-6 Sol better than Mistral Large 4 for coding?
Pick GPT-6 Sol for coding: it scores 76.0 on the Vibe Coding Index against 56.4 for Mistral Large 4. Pick Mistral Large 4 for output tokens 2.4x cheaper ($4.18 vs $10.00 per million) and work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.
Which is cheaper, GPT-6 Sol or Mistral Large 4?
GPT-6 Sol costs $2.00 per million input tokens and $10.00 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 Sol or Mistral Large 4?
GPT-6 Sol, with 1.05M tokens against 1.05M.
How many benchmarks is the GPT-6 Sol vs Mistral Large 4 comparison based on?
77 benchmarks have a result for both models as of October 22, 2026. GPT-6 Sol's coding index rests on 5 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.