GLM 5V Turbo vs Mistral Medium 3
GLM 5V Turbo leads Mistral Medium 3 on the Artificial Analysis Intelligence Index, 23.5 to 9.0, and Mistral Medium 3 costs 2.0x less per output token ($2.00 vs $4.00 per million). Updated October 21, 2026; 50 benchmarks have a result for both.
GLM 5V Turbo or Mistral Medium 3: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick GLM 5V Turbo for a larger context window (203K against 131K tokens).
- Shared results
- 50
- GLM 5V Turbo only
- 15
- Mistral Medium 3 only
- 7
- 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
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
GLM 5V Turbo
GLM 5V Turbo leads, 23.5 against 9.0.
Same board, both measured
Web design
Design Arena: websites
GLM 5V Turbo
GLM 5V Turbo leads, 1230 against 1079.
Same board, both measured
Long documents
Listed context window
GLM 5V Turbo
GLM 5V Turbo takes 203K tokens against 131K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Mistral Medium 3
GLM 5V Turbo $0.0032, Mistral Medium 3 $0.0014 per turn.
List prices
At a glance
- Coding index
- GLM 5V Turbo not benchmarked, Mistral Medium 3 not benchmarked.
- Widest category
- Agentic work, 74.3 points apart on average over 1 shared benchmark.
- Widest single gap
- τ²-Bench Telecom: GLM 5V Turbo 98.5% against Mistral Medium 3 24.3%, 74.3 points apart on a 0 to 100 scale.
- Output price
- GLM 5V Turbo $4.00 against Mistral Medium 3 $2.00 per million output tokens, 2.0x apart.
- Context window
- GLM 5V Turbo takes 203K tokens, Mistral Medium 3 131K.
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 5V Turbo | Bars | Mistral Medium 3 | Ties |
|---|---|---|---|---|
| Coding | 3 | 0 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 7 | 0 | ||
| Math | 2 | 0 | ||
| Knowledge | 4 | 0 | ||
| Web design | 6 | 0 | ||
| General | 26 | 0 | ||
| All shared boards | 50 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index30
| Benchmark | GLM 5V Turbo | Mistral Medium 3 | Leader |
|---|---|---|---|
| LMArena WebDev | 1402 | Not measured | Only GLM 5V Turbo measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 40.0% | Only Mistral Medium 3 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 32.6% | 3.8% | GLM 5V Turbo |
| LMArena Text: coding | 1466 | 1385 | GLM 5V Turbo |
| LMArena Text: software and IT | 1460 | 1385 | GLM 5V Turbo |
| LMArena WebDev: React | 1386 | Not measured | Only GLM 5V Turbo measured |
| LMArena WebDev: HTML | 1356 | Not measured | Only GLM 5V Turbo measured |
| LMArena WebDev: from an image | 1425 | Not measured | Only GLM 5V Turbo measured |
| Neither model has a result on the other 31 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GLM 5V Turbo | Mistral Medium 3 | Leader |
|---|---|---|---|
| AA Intelligence Index | 23.5 | 9.0 | GLM 5V Turbo |
| Epoch Capabilities Index | Not measured | 134.0 | Only Mistral Medium 3 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GLM 5V Turbo | Mistral Medium 3 | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | 1124 | Not measured | Only GLM 5V Turbo measured |
| Design Arena: agents building full-stack apps | 1149 | Not measured | Only GLM 5V Turbo measured |
| Design Arena: agents building mobile apps | 1134 | Not measured | Only GLM 5V Turbo measured |
| Design Arena: agents building Android apps | 1267 | Not measured | Only GLM 5V Turbo measured |
| Design Arena: agents building Godot games | 957 | Not measured | Only GLM 5V Turbo measured |
| Design Arena: agents building games | 1102 | Not measured | Only GLM 5V Turbo measured |
| Design Arena: HTML slides | 1120 | Not measured | Only GLM 5V Turbo measured |
| Design Arena: PowerPoint slides | 1152 | Not measured | Only GLM 5V Turbo measured |
| τ²-Bench Telecom | 98.5% | 24.3% | GLM 5V Turbo |
| Neither model has a result on the other 32 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index70
| Benchmark | GLM 5V Turbo | Mistral Medium 3 | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 80.9% | 57.8% | GLM 5V Turbo |
| Humanity's Last Exam (Artificial Analysis run) | 17.1% | 4.1% | GLM 5V Turbo |
| LMArena Text: hard prompts | 1443 | 1364 | GLM 5V Turbo |
| LMArena Text: expert | 1453 | 1342 | GLM 5V Turbo |
| LMArena Text: hard prompts in English | 1456 | 1374 | GLM 5V Turbo |
| LMArena Vision: diagrams | 1286 | 1155 | GLM 5V Turbo |
| LMArena Vision: homework | 1273 | 1165 | GLM 5V Turbo |
| Neither model has a result on the other 15 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | GLM 5V Turbo | Mistral Medium 3 | Leader |
|---|---|---|---|
| AA Math Index | Not measured | 30.3 | Only Mistral Medium 3 measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 30.3% | Only Mistral Medium 3 measured |
| LMArena Text: math | 1442 | 1353 | GLM 5V Turbo |
| LMArena Text: mathematical work | 1447 | 1354 | GLM 5V Turbo |
| Neither model has a result on the other 9 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | GLM 5V Turbo | Mistral Medium 3 | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | Not measured | 76.0% | Only Mistral Medium 3 measured |
| LMArena Text: science | 1448 | 1381 | GLM 5V Turbo |
| LMArena Text: medicine and healthcare | 1433 | 1381 | GLM 5V Turbo |
| LMArena Text: legal and government | 1436 | 1384 | GLM 5V Turbo |
| LMArena Text: business and finance | 1435 | 1352 | GLM 5V Turbo |
| Neither model has a result on the other 13 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | GLM 5V Turbo | Mistral Medium 3 | Leader |
|---|---|---|---|
| Design Arena: websites | 1230 | 1079 | GLM 5V Turbo |
| Design Arena: UI components | 1213 | 1024 | GLM 5V Turbo |
| Design Arena: game dev | 1219 | 1018 | GLM 5V Turbo |
| Design Arena: data viz | 1202 | 1034 | GLM 5V Turbo |
| Design Arena: 3D | 1209 | 1084 | GLM 5V Turbo |
| Design Arena: all code categories | 1228 | 1069 | GLM 5V Turbo |
| Design Arena: SVG | 1151 | Not measured | Only GLM 5V Turbo measured |
| Design Arena: ASCII art | 1117 | Not measured | Only GLM 5V Turbo measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index260
| Benchmark | GLM 5V Turbo | Mistral Medium 3 | Leader |
|---|---|---|---|
| IFBench | 61.1% | 39.3% | GLM 5V Turbo |
| Long context reasoning (AA-LCR) | 70.3% | 31.3% | GLM 5V Turbo |
| DTBench | Not measured | 62.3% | Only Mistral Medium 3 measured |
| LMArena Text | 1437 | 1370 | GLM 5V Turbo |
| LMArena Text: instruction following | 1423 | 1338 | GLM 5V Turbo |
| LMArena Text: creative writing | 1417 | 1343 | GLM 5V Turbo |
| LMArena Vision | 1264 | 1157 | GLM 5V Turbo |
| LMArena Text: English | 1454 | 1385 | GLM 5V Turbo |
| LMArena Text: non-English | 1420 | 1353 | GLM 5V Turbo |
| LMArena Text: Chinese | 1491 | 1374 | GLM 5V Turbo |
| LMArena Text: German | 1422 | 1377 | GLM 5V Turbo |
| LMArena Text: Japanese | Not measured | 1316 | Only Mistral Medium 3 measured |
| LMArena Text: Korean | 1397 | 1304 | GLM 5V Turbo |
| LMArena Text: French | 1443 | 1368 | GLM 5V Turbo |
| LMArena Text: Spanish | 1452 | 1364 | GLM 5V Turbo |
| LMArena Text: Russian | 1432 | 1359 | GLM 5V Turbo |
| LMArena Text: Polish | 1432 | 1371 | GLM 5V Turbo |
| LMArena Text: multi-turn | 1431 | 1384 | GLM 5V Turbo |
| LMArena Text: longer queries | 1438 | 1360 | GLM 5V Turbo |
| LMArena Text: writing and language | 1420 | 1352 | GLM 5V Turbo |
| LMArena Text: entertainment and media | 1407 | 1335 | GLM 5V Turbo |
| LMArena Vision: English | 1274 | 1172 | GLM 5V Turbo |
| LMArena Vision: Chinese | 1329 | 1161 | GLM 5V Turbo |
| LMArena Vision: reading text | 1270 | 1154 | GLM 5V Turbo |
| LMArena Vision: humor | 1268 | 1145 | GLM 5V Turbo |
| LMArena Vision: captioning | 1264 | 1094 | GLM 5V Turbo |
| LMArena Vision: recognizing things | 1241 | 1141 | GLM 5V Turbo |
| LMArena Vision: creative writing | 1252 | 1146 | GLM 5V Turbo |
| LMArena Document | 1416 | Not measured | Only GLM 5V Turbo measured |
| Neither model has a result on the other 17 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GLM 5V Turbo | Mistral Medium 3 | 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 costs less
Repository review
50K input + 3K output tokens
Mistral Medium 3 costs less
Agent loop
200K input + 10K output tokens
Mistral Medium 3 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 5V Turbo | Mistral Medium 3 |
|---|---|---|
| Maker | Z.ai | Mistral AI |
| Weights | No public weights listed | No public weights listed |
| Released | April 1, 2026 | May 7, 2025 |
| Context window | 203K | 131K |
| Input $/Mtok | $1.20 | $0.40 |
| Output $/Mtok | $4.00 | $2.00 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 1 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GLM 5V Turbo better than Mistral Medium 3 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GLM 5V Turbo for a larger context window (203K against 131K tokens).
Which is cheaper, GLM 5V Turbo or Mistral Medium 3?
GLM 5V Turbo costs $1.20 per million input tokens and $4.00 per million output tokens; Mistral Medium 3 costs $0.40 and $2.00. Cost per solved task is known for neither of them.
Which has the bigger context window, GLM 5V Turbo or Mistral Medium 3?
GLM 5V Turbo, with 203K tokens against 131K.
How many benchmarks is the GLM 5V Turbo vs Mistral Medium 3 comparison based on?
50 benchmarks have a result for both models as of October 21, 2026. GLM 5V Turbo's coding index rests on 1 independent benchmark and Mistral Medium 3's on 0. Where only one model has a result, the page says so instead of naming a winner.