GLM 5.2 vs Mistral Large 4
GLM 5.2 leads Mistral Large 4 on coding, 61.1 to 56.4 on the Vibe Coding Index, at about the same output price ($4.40 vs $4.18 per million). Updated October 22, 2026; 61 benchmarks have a result for both.
GLM 5.2 or Mistral Large 4: which to pick
Pick GLM 5.2 for coding: it scores 61.1 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 1.1x cheaper ($4.18 vs $4.40 per million) and work measured by Vibe Code Bench (Vals AI) or SciCode, where it leads.
- Shared results
- 61
- GLM 5.2 only
- 37
- Mistral Large 4 only
- 20
- 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
GLM 5.2
GLM 5.2 scores 61.1 against 56.4.
4 and 5 benchmarks behind the scores
Intelligence
AA Intelligence Index
Mistral Large 4
Mistral Large 4 leads, 38.4 against 33.7.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only GLM 5.2 has a AA Agentic Index result, 38.4.
Directional only
Reasoning
GPQA Diamond
No call
Only GLM 5.2 has a GPQA Diamond result, 85.6%.
Directional only
Knowledge
MMLU Pro
No call
Only GLM 5.2 has a MMLU Pro result, 86.7%.
Directional only
Web design
Design Arena: websites
GLM 5.2
GLM 5.2 leads, 1285 against 1257.
Same board, both measured
Long documents
Listed context window
No call
Both take 1.05M tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Mistral Large 4
GLM 5.2 $0.0036, Mistral Large 4 $0.0034 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GLM 5.2 has the number, $0.86.
Directional only
At a glance
- Coding index
- GLM 5.2 61.1 from 4 benchmarks, Mistral Large 4 56.4 from 5 benchmarks.
- Widest category
- Coding, 8.7 points apart on average over 10 shared benchmarks.
- Widest single gap
- Surface Evolver Bench: GLM 5.2 55.6% against Mistral Large 4 28.1%, 27.5 points apart on a 0 to 100 scale.
- Output price
- GLM 5.2 $4.40 against Mistral Large 4 $4.18 per million output tokens, 1.1x apart.
- Context window
- Both take 1.05M tokens.
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 | GLM 5.2 | Bars | Mistral Large 4 | Ties |
|---|---|---|---|---|
| Coding | 6 | 4 | ||
| Intelligence | 1 | 1 | ||
| Agentic work | 1 | 2 | ||
| Reasoning | 6 | 1 | ||
| Math | 5 | 1 | ||
| Knowledge | 6 | 0 | ||
| Web design | 6 | 2 | ||
| General | 17 | 2 | ||
| All shared boards | 48 | 13 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index64
| Benchmark | GLM 5.2 | Mistral Large 4 | Leader |
|---|---|---|---|
| LiveBench coding | Not measured | 60.0% | Only Mistral Large 4 measured |
| LMArena WebDev | 1604 | 1543 | GLM 5.2 |
| AA Coding Index | 68.8 | Not measured | Only GLM 5.2 measured |
| LiveCodeBench (Vals AI) | 69.5% | Not measured | Only GLM 5.2 measured |
| SWE-bench Verified (Vals AI) | 82.8% | Not measured | Only GLM 5.2 measured |
| Terminal-Bench 4 (Vals AI) | Not measured | 27.8% | Only Mistral Large 4 measured |
| Vibe Code Bench (Vals AI) | 64.0% | 78.4% | Mistral Large 4 |
| Code migration (Vals AI) | 37.9% | 30.6% | GLM 5.2 |
| ProgramBench (Vals AI) | 0.5% | Not measured | Only GLM 5.2 measured |
| IOI (Vals AI) | Not measured | 45.3% | Only Mistral Large 4 measured |
| Terminal-Bench 2.1 (Vals AI) | 67.8% | Not measured | Only GLM 5.2 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 |
| SkillsBench (Vals AI) | 45.1% | Not measured | Only GLM 5.2 measured |
| SciCode | 51.2% | 54.2% | Mistral Large 4 |
| Terminal-Bench Hard (Artificial Analysis run) | 50.8% | Not measured | Only GLM 5.2 measured |
| FrontierCode | 24.5% | 39.4% | Mistral Large 4 |
| WeirdML | 70.1% | Not measured | Only GLM 5.2 measured |
| ALE-Bench | 1047.0 | 1213.2 | Mistral Large 4 |
| LMArena Text: coding | 1487 | 1478 | GLM 5.2 |
| LMArena Text: software and IT | 1486 | 1467 | GLM 5.2 |
| LMArena WebDev: React | 1617 | 1559 | GLM 5.2 |
| LMArena WebDev: HTML | 1565 | 1487 | GLM 5.2 |
| Neither model has a result on the other 16 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | GLM 5.2 | Mistral Large 4 | Leader |
|---|---|---|---|
| AA Intelligence Index | 33.7 | 38.4 | Mistral Large 4 |
| Epoch Capabilities Index | 151.9 | 150.0 | GLM 5.2 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index12
| Benchmark | GLM 5.2 | Mistral Large 4 | Leader |
|---|---|---|---|
| AA Agentic Index | 38.4 | Not measured | Only GLM 5.2 measured |
| Design Arena: agents building web apps | 1222 | Not measured | Only GLM 5.2 measured |
| Design Arena: agents building full-stack apps | 1241 | Not measured | Only GLM 5.2 measured |
| Design Arena: agents building mobile apps | 1159 | Not measured | Only GLM 5.2 measured |
| Design Arena: agents building Android apps | 1178 | Not measured | Only GLM 5.2 measured |
| Design Arena: agents building Godot games | 1142 | Not measured | Only GLM 5.2 measured |
| Design Arena: agents building games | 1206 | Not measured | Only GLM 5.2 measured |
| Design Arena: HTML slides | 1125 | Not measured | Only GLM 5.2 measured |
| Design Arena: PowerPoint slides | 1170 | Not measured | Only GLM 5.2 measured |
| LiveBench research | Not measured | 28.1% | Only Mistral Large 4 measured |
| LiveBench browser | Not measured | 8.0% | Only Mistral Large 4 measured |
| LiveBench long agentic | Not measured | 11.8% | Only Mistral Large 4 measured |
| SREBench (Vals AI) | 0.0% | Not measured | Only GLM 5.2 measured |
| Finance Agent (Vals AI) | 49.7% | 54.7% | Mistral Large 4 |
| Tax Agent Bench (Vals AI) | Not measured | 30.4% | Only Mistral Large 4 measured |
| Legal Research Bench (Vals AI) | 31.3% | 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) | 61.5% | 56.2% | GLM 5.2 |
| BioMysteryBench (Vals AI) | Not measured | 67.0% | Only Mistral Large 4 measured |
| τ²-Bench Telecom | 99.1% | Not measured | Only GLM 5.2 measured |
| APEX-Agents | 45.2% | Not measured | Only GLM 5.2 measured |
| PostTrainBench | 31.7% | Not measured | Only GLM 5.2 measured |
| Vending-Bench 2 | $8,314 | Not measured | Only GLM 5.2 measured |
| Neither model has a result on the other 18 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index61
| Benchmark | GLM 5.2 | Mistral Large 4 | Leader |
|---|---|---|---|
| GPQA Diamond | 85.6% | Not measured | Only GLM 5.2 measured |
| LiveBench reasoning | Not measured | 83.9% | Only Mistral Large 4 measured |
| MysteryMechanism (Vals AI) | Not measured | 12.2% | Only Mistral Large 4 measured |
| GPQA Diamond (Artificial Analysis run) | 89.5% | Not measured | Only GLM 5.2 measured |
| Humanity's Last Exam (Artificial Analysis run) | 41.1% | 35.0% | GLM 5.2 |
| GPQA Diamond (Epoch AI run) | 91.9% | 88.1% | GLM 5.2 |
| ARC-AGI | 77.0% | Not measured | Only GLM 5.2 measured |
| ARC-AGI-2 | 22.8% | Not measured | Only GLM 5.2 measured |
| SimpleBench | 58.8% | Not measured | Only GLM 5.2 measured |
| Chess puzzles | 22.0% | 33.0% | Mistral Large 4 |
| Mystery game puzzles | 19.0% | 17.0% | GLM 5.2 |
| EBR-bench | 9.5% | Not measured | Only GLM 5.2 measured |
| LMArena Text: hard prompts | 1481 | 1444 | GLM 5.2 |
| LMArena Text: expert | 1487 | 1444 | GLM 5.2 |
| LMArena Text: hard prompts in English | 1481 | 1442 | GLM 5.2 |
| LMArena Vision: diagrams | Not measured | 1288 | Only Mistral Large 4 measured |
| Kagi LLM Benchmark | 62.6% | Not measured | Only GLM 5.2 measured |
| Neither model has a result on the other 5 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index51
| Benchmark | GLM 5.2 | Mistral Large 4 | Leader |
|---|---|---|---|
| OTIS Mock AIME | 86.4% | 98.3% | Mistral Large 4 |
| FrontierMath, tiers 1 to 3 | 59.2% | 58.6% | GLM 5.2 |
| FrontierMath, tier 4 | 29.3% | 26.8% | GLM 5.2 |
| ProofBench | 35.0% | 10.0% | GLM 5.2 |
| LMArena Text: math | 1483 | 1469 | GLM 5.2 |
| LMArena Text: mathematical work | 1489 | 1462 | GLM 5.2 |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | GLM 5.2 | Mistral Large 4 | Leader |
|---|---|---|---|
| MMLU Pro | 86.7% | Not measured | Only GLM 5.2 measured |
| LegalBench (Vals AI) | 84.1% | Not measured | Only GLM 5.2 measured |
| CorpFin (Vals AI) | 66.1% | Not measured | Only GLM 5.2 measured |
| TaxEval (Vals AI) | 73.3% | Not measured | Only GLM 5.2 measured |
| MedCode (Vals AI) | 40.8% | 40.7% | GLM 5.2 |
| SimpleQA Verified | 34.2% | 20.0% | GLM 5.2 |
| LMArena Text: science | 1489 | 1448 | GLM 5.2 |
| LMArena Text: medicine and healthcare | 1475 | 1433 | GLM 5.2 |
| LMArena Text: legal and government | 1486 | 1425 | GLM 5.2 |
| LMArena Text: business and finance | 1451 | 1439 | GLM 5.2 |
| Neither model has a result on the other 8 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index62
| Benchmark | GLM 5.2 | Mistral Large 4 | Leader |
|---|---|---|---|
| Design Arena: websites | 1285 | 1257 | GLM 5.2 |
| Design Arena: UI components | 1294 | 1272 | GLM 5.2 |
| Design Arena: game dev | 1268 | 1225 | GLM 5.2 |
| Design Arena: data viz | 1285 | 1275 | GLM 5.2 |
| Design Arena: 3D | 1287 | 1252 | GLM 5.2 |
| Design Arena: all code categories | 1287 | 1259 | GLM 5.2 |
| Design Arena: SVG | 1213 | 1232 | Mistral Large 4 |
| Design Arena: ASCII art | 1191 | 1202 | Mistral Large 4 |
| LiveBench design | Not measured | 65.6% | Only Mistral Large 4 measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index172
| Benchmark | GLM 5.2 | Mistral Large 4 | Leader |
|---|---|---|---|
| LiveBench data analysis | Not measured | 76.5% | Only Mistral Large 4 measured |
| MedScribe (Vals AI) | 83.5% | 80.4% | GLM 5.2 |
| IFBench | 73.3% | Not measured | Only GLM 5.2 measured |
| Long context reasoning (AA-LCR) | 78.3% | 81.3% | Mistral Large 4 |
| DTBench | 93.6% | 88.2% | GLM 5.2 |
| LMCA | 45.8% | 35.8% | GLM 5.2 |
| Surface Evolver Bench | 55.6% | 28.1% | GLM 5.2 |
| Furniture assembly | Not measured | 20.8% | Only Mistral Large 4 measured |
| LMArena Text | 1470 | 1431 | GLM 5.2 |
| LMArena Text: instruction following | 1466 | 1422 | GLM 5.2 |
| LMArena Text: creative writing | 1463 | 1363 | GLM 5.2 |
| LMArena Vision | Not measured | 1272 | Only Mistral Large 4 measured |
| LMArena Text: English | 1475 | 1433 | GLM 5.2 |
| LMArena Text: non-English | 1459 | 1422 | GLM 5.2 |
| LMArena Text: Chinese | 1522 | 1492 | GLM 5.2 |
| LMArena Text: German | 1470 | Not measured | Only GLM 5.2 measured |
| LMArena Text: Japanese | 1450 | 1415 | GLM 5.2 |
| LMArena Text: Korean | 1440 | Not measured | Only GLM 5.2 measured |
| LMArena Text: French | 1479 | 1492 | Mistral Large 4 |
| LMArena Text: Spanish | 1478 | 1455 | GLM 5.2 |
| LMArena Text: Russian | 1468 | 1417 | GLM 5.2 |
| LMArena Text: Polish | 1456 | Not measured | Only GLM 5.2 measured |
| LMArena Text: multi-turn | 1469 | 1435 | GLM 5.2 |
| LMArena Text: longer queries | 1480 | 1428 | GLM 5.2 |
| LMArena Text: writing and language | 1463 | 1386 | GLM 5.2 |
| LMArena Text: entertainment and media | 1450 | 1378 | GLM 5.2 |
| LMArena Vision: English | Not measured | 1283 | Only Mistral Large 4 measured |
| LMArena Vision: reading text | Not measured | 1284 | Only Mistral Large 4 measured |
| Neither model has a result on the other 18 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GLM 5.2 | 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 | Z.ai GLM 5.2 | Mistral Large 4 |
|---|---|---|
| Maker | Z.ai | Mistral AI |
| Weights | Open weights | No public weights listed |
| Released | June 16, 2026 | October 6, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $1.40 | $1.36 |
| Output $/Mtok | $4.40 | $4.18 |
| Coding index | 61.1 | 56.4 |
| Independent measurements behind it | 4 | 5 |
| Cost per solved task | $0.86 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GLM 5.2 better than Mistral Large 4 for coding?
Pick GLM 5.2 for coding: it scores 61.1 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 1.1x cheaper ($4.18 vs $4.40 per million) and work measured by Vibe Code Bench (Vals AI) or SciCode, where it leads.
Which is cheaper, GLM 5.2 or Mistral Large 4?
GLM 5.2 costs $1.40 per million input tokens and $4.40 per million output tokens; Mistral Large 4 costs $1.36 and $4.18. Cost per solved task is known for GLM 5.2 only.
Which has the bigger context window, GLM 5.2 or Mistral Large 4?
Neither: both take 1.05M tokens.
How many benchmarks is the GLM 5.2 vs Mistral Large 4 comparison based on?
61 benchmarks have a result for both models as of October 22, 2026. GLM 5.2'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.