GLM 5.1 vs Mistral Small 4
Updated October 21, 2026. 12 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Only GLM 5.1 has a coding score, 49.2 on the Vibe Coding Index; Mistral Small 4 has none, so the two cannot be ranked on coding.
Mistral Small 4 has the edge where output tokens cost 7.3x less, and where the context window is larger, 262K against 205K tokens.
- Shared results
- 12
- GLM 5.1 only
- 77
- Mistral Small 4 only
- 2
- Like-for-like categories
- 5 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
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
No call
Only GLM 5.1 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
GLM 5.1
GLM 5.1 leads, 26.1 against 11.3.
Same board, both measured
Agentic work
AA Agentic Index
GLM 5.1
GLM 5.1 leads, 23.9 against 0.8.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only GLM 5.1 has a GPQA Diamond result, 84.5%.
Directional only
Math
AIME
No call
Only GLM 5.1 has a AIME result, 91.9%.
Directional only
Knowledge
MMLU Pro
No call
Only GLM 5.1 has a MMLU Pro result, 86.9%.
Directional only
Web design
Design Arena: websites
No call
Only GLM 5.1 has a Design Arena: websites result, 1290.
Directional only
Long documents
Listed context window
Mistral Small 4
Mistral Small 4 takes 262K tokens against 205K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Mistral Small 4
GLM 5.1 $0.0036, Mistral Small 4 $0.0004 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GLM 5.1 has the number, $0.60.
Directional only
At a glance
- Coding index
- GLM 5.1 49.2 from 3 benchmarks, Mistral Small 4 not benchmarked.
- Widest category
- Agentic work, 39.8 points apart on average over 2 shared benchmarks.
- Widest single gap
- τ²-Bench Telecom: GLM 5.1 97.7% against Mistral Small 4 41.2%, 56.4 points apart on a 0 to 100 scale.
- Output price
- GLM 5.1 $4.40 against Mistral Small 4 $0.60 per million output tokens, 7.3x apart.
- Context window
- GLM 5.1 takes 205K tokens, Mistral Small 4 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 | GLM 5.1 | Bars | Mistral Small 4 | Ties |
|---|---|---|---|---|
| Coding | 5 | 0 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 2 | 0 | ||
| Reasoning | 2 | 0 | ||
| General | 2 | 0 | ||
| All shared boards | 12 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index50
| Benchmark | GLM 5.1 | Mistral Small 4 | Leader |
|---|---|---|---|
| LMArena WebDev | 1508 | Not measured | Only GLM 5.1 measured |
| AA Coding Index | 55.8 | 26.6 | GLM 5.1 |
| LiveCodeBench (Vals AI) | 81.4% | Not measured | Only GLM 5.1 measured |
| SWE-bench Verified (Vals AI) | 76.4% | Not measured | Only GLM 5.1 measured |
| Vibe Code Bench (Vals AI) | 31.5% | 0.0% | GLM 5.1 |
| Code migration (Vals AI) | 25.8% | Not measured | Only GLM 5.1 measured |
| ProgramBench (Vals AI) | 0.0% | Not measured | Only GLM 5.1 measured |
| Terminal-Bench 2.1 (Vals AI) | 56.9% | Not measured | Only GLM 5.1 measured |
| SciCode | 44.8% | 38.8% | GLM 5.1 |
| Terminal-Bench Hard (Artificial Analysis run) | 43.2% | 17.4% | GLM 5.1 |
| WeirdML | 57.1% | Not measured | Only GLM 5.1 measured |
| ALE-Bench | 887.1 | 497.6 | GLM 5.1 |
| LMArena Text: coding | 1485 | Not measured | Only GLM 5.1 measured |
| LMArena Text: software and IT | 1484 | Not measured | Only GLM 5.1 measured |
| LMArena WebDev: React | 1505 | Not measured | Only GLM 5.1 measured |
| LMArena WebDev: HTML | 1508 | Not measured | Only GLM 5.1 measured |
| Neither model has a result on the other 22 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GLM 5.1 | Mistral Small 4 | Leader |
|---|---|---|---|
| AA Intelligence Index | 26.1 | 11.3 | GLM 5.1 |
| Epoch Capabilities Index | 149.8 | Not measured | Only GLM 5.1 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | GLM 5.1 | Mistral Small 4 | Leader |
|---|---|---|---|
| AA Agentic Index | 23.9 | 0.8 | GLM 5.1 |
| Design Arena: agents building web apps | 1175 | Not measured | Only GLM 5.1 measured |
| Design Arena: agents building full-stack apps | 1167 | Not measured | Only GLM 5.1 measured |
| Design Arena: agents building mobile apps | 1161 | Not measured | Only GLM 5.1 measured |
| Design Arena: agents building Android apps | 1187 | Not measured | Only GLM 5.1 measured |
| Design Arena: agents building Godot games | 1053 | Not measured | Only GLM 5.1 measured |
| Design Arena: agents building games | 1164 | Not measured | Only GLM 5.1 measured |
| Design Arena: HTML slides | 1170 | Not measured | Only GLM 5.1 measured |
| Design Arena: PowerPoint slides | 1188 | Not measured | Only GLM 5.1 measured |
| Design Arena: spreadsheets | 1315 | Not measured | Only GLM 5.1 measured |
| Finance Agent (Vals AI) | 44.8% | Not measured | Only GLM 5.1 measured |
| Legal Research Bench (Vals AI) | 27.9% | Not measured | Only GLM 5.1 measured |
| τ²-Bench Telecom | 97.7% | 41.2% | GLM 5.1 |
| APEX-Agents | 40.9% | Not measured | Only GLM 5.1 measured |
| Vending-Bench 2 | $5,634 | Not measured | Only GLM 5.1 measured |
| Neither model has a result on the other 24 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | GLM 5.1 | Mistral Small 4 | Leader |
|---|---|---|---|
| GPQA Diamond | 84.5% | Not measured | Only GLM 5.1 measured |
| GPQA Diamond (Artificial Analysis run) | 86.8% | 76.9% | GLM 5.1 |
| Humanity's Last Exam (Artificial Analysis run) | 30.1% | 9.9% | GLM 5.1 |
| GPQA Diamond (Epoch AI run) | 89.9% | Not measured | Only GLM 5.1 measured |
| SimpleBench | 55.1% | Not measured | Only GLM 5.1 measured |
| Chess puzzles | 20.0% | Not measured | Only GLM 5.1 measured |
| LMArena Text: hard prompts | 1473 | Not measured | Only GLM 5.1 measured |
| LMArena Text: expert | 1478 | Not measured | Only GLM 5.1 measured |
| LMArena Text: hard prompts in English | 1482 | Not measured | Only GLM 5.1 measured |
| Neither model has a result on the other 12 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | GLM 5.1 | Mistral Small 4 | Leader |
|---|---|---|---|
| AIME | 91.9% | Not measured | Only GLM 5.1 measured |
| OTIS Mock AIME | 93.3% | Not measured | Only GLM 5.1 measured |
| FrontierMath, tiers 1 to 3 | 36.8% | Not measured | Only GLM 5.1 measured |
| ProofBench | 22.2% | Not measured | Only GLM 5.1 measured |
| LMArena Text: math | 1473 | Not measured | Only GLM 5.1 measured |
| LMArena Text: mathematical work | 1470 | Not measured | Only GLM 5.1 measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index11 boards, none shared
| Benchmark | GLM 5.1 | Mistral Small 4 | Leader |
|---|---|---|---|
| MMLU Pro | 86.9% | Not measured | Only GLM 5.1 measured |
| LegalBench (Vals AI) | 84.4% | Not measured | Only GLM 5.1 measured |
| CaseLaw (Vals AI) | 51.5% | Not measured | Only GLM 5.1 measured |
| CorpFin (Vals AI) | 64.5% | Not measured | Only GLM 5.1 measured |
| TaxEval (Vals AI) | 71.2% | Not measured | Only GLM 5.1 measured |
| MedCode (Vals AI) | 41.6% | Not measured | Only GLM 5.1 measured |
| SimpleQA Verified | 34.0% | Not measured | Only GLM 5.1 measured |
| LMArena Text: science | 1478 | Not measured | Only GLM 5.1 measured |
| LMArena Text: medicine and healthcare | 1474 | Not measured | Only GLM 5.1 measured |
| LMArena Text: legal and government | 1465 | Not measured | Only GLM 5.1 measured |
| LMArena Text: business and finance | 1452 | Not measured | Only GLM 5.1 measured |
| Neither model has a result on the other 6 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | GLM 5.1 | Mistral Small 4 | Leader |
|---|---|---|---|
| Design Arena: websites | 1290 | Not measured | Only GLM 5.1 measured |
| Design Arena: UI components | 1292 | Not measured | Only GLM 5.1 measured |
| Design Arena: game dev | 1265 | Not measured | Only GLM 5.1 measured |
| Design Arena: data viz | 1366 | Not measured | Only GLM 5.1 measured |
| Design Arena: 3D | 1336 | Not measured | Only GLM 5.1 measured |
| Design Arena: all code categories | 1268 | Not measured | Only GLM 5.1 measured |
| Design Arena: SVG | 1218 | Not measured | Only GLM 5.1 measured |
| Design Arena: ASCII art | 1142 | Not measured | Only GLM 5.1 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | GLM 5.1 | Mistral Small 4 | Leader |
|---|---|---|---|
| Public Benefits Bench (Vals AI) | 61.8% | Not measured | Only GLM 5.1 measured |
| MedScribe (Vals AI) | 72.3% | Not measured | Only GLM 5.1 measured |
| IFBench | 76.3% | 48.2% | GLM 5.1 |
| Long context reasoning (AA-LCR) | 73.7% | 49.7% | GLM 5.1 |
| DTBench | Not measured | 70.9% | Only Mistral Small 4 measured |
| LMCA | Not measured | 20.6% | Only Mistral Small 4 measured |
| ExploitBench | 18.1% | Not measured | Only GLM 5.1 measured |
| LMArena Text | 1463 | Not measured | Only GLM 5.1 measured |
| LMArena Text: instruction following | 1453 | Not measured | Only GLM 5.1 measured |
| LMArena Text: creative writing | 1453 | Not measured | Only GLM 5.1 measured |
| LMArena Text: English | 1476 | Not measured | Only GLM 5.1 measured |
| LMArena Text: non-English | 1448 | Not measured | Only GLM 5.1 measured |
| LMArena Text: Chinese | 1515 | Not measured | Only GLM 5.1 measured |
| LMArena Text: German | 1467 | Not measured | Only GLM 5.1 measured |
| LMArena Text: Japanese | 1435 | Not measured | Only GLM 5.1 measured |
| LMArena Text: Korean | 1424 | Not measured | Only GLM 5.1 measured |
| LMArena Text: French | 1470 | Not measured | Only GLM 5.1 measured |
| LMArena Text: Spanish | 1468 | Not measured | Only GLM 5.1 measured |
| LMArena Text: Russian | 1454 | Not measured | Only GLM 5.1 measured |
| LMArena Text: Polish | 1449 | Not measured | Only GLM 5.1 measured |
| LMArena Text: multi-turn | 1473 | Not measured | Only GLM 5.1 measured |
| LMArena Text: longer queries | 1467 | Not measured | Only GLM 5.1 measured |
| LMArena Text: writing and language | 1454 | Not measured | Only GLM 5.1 measured |
| LMArena Text: entertainment and media | 1442 | Not measured | Only GLM 5.1 measured |
| Neither model has a result on the other 22 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GLM 5.1 | Mistral Small 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 Small 4 costs less
Repository review
50K input + 3K output tokens
Mistral Small 4 costs less
Agent loop
200K input + 10K output tokens
Mistral Small 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 5.1 | Mistral Small 4 |
|---|---|---|
| Maker | Z.ai | Mistral AI |
| Weights | Open weights | Open weights |
| Released | April 7, 2026 | March 16, 2026 |
| Context window | 205K | 262K |
| Input $/Mtok | $1.40 | $0.15 |
| Output $/Mtok | $4.40 | $0.60 |
| Coding index | 49.2 | Not benchmarked |
| Independent measurements behind it | 3 | 1 |
| Cost per solved task | $0.60 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GLM 5.1 better than Mistral Small 4 for coding?
Only GLM 5.1 has a coding score, 49.2 on the Vibe Coding Index; Mistral Small 4 has none, so the two cannot be ranked on coding. Mistral Small 4 has the edge where output tokens cost 7.3x less, and where the context window is larger, 262K against 205K tokens.
Which is cheaper, GLM 5.1 or Mistral Small 4?
GLM 5.1 costs $1.40 per million input tokens and $4.40 per million output tokens; Mistral Small 4 costs $0.15 and $0.60. Cost per solved task is known for GLM 5.1 only.
Which has the bigger context window, GLM 5.1 or Mistral Small 4?
Mistral Small 4, with 262K tokens against 205K.
How many benchmarks is the GLM 5.1 vs Mistral Small 4 comparison based on?
12 benchmarks have a result for both models as of October 21, 2026. GLM 5.1's coding index rests on 3 independent benchmarks and Mistral Small 4's on 1. Where only one model has a result, the page says so instead of naming a winner.