Codestral 2508 vs GLM 4.6V
Codestral 2508 and GLM 4.6V cost about the same per output token ($0.90 vs $0.90 per million). Updated October 21, 2026; no benchmark has tested both models yet.
- Coding
- No data
- Overall
- No data
- Output $/M
- $0.90
- Coding
- No data
- Overall
- No data
- Output $/M
- $0.90
Codestral 2508 or GLM 4.6V: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Codestral 2508 for a larger context window (256K against 131K tokens).
No benchmark has tested both yet. Codestral 2508 has results on ALE-Bench, Kagi LLM Benchmark and Design Arena: websites; GLM 4.6V on LiveCodeBench (Artificial Analysis run), Terminal-Bench Hard (Artificial Analysis run) and LMArena Text: coding. Compare them on price and context instead.
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
No call
Only GLM 4.6V has a AA Intelligence Index result, 11.2.
Directional only
Web design
Design Arena: websites
No call
Only Codestral 2508 has a Design Arena: websites result, 1013.
Directional only
Long documents
Listed context window
Codestral 2508
Codestral 2508 takes 256K tokens against 131K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
No call
Codestral 2508 $0.0008, GLM 4.6V $0.0008 per turn.
List prices
At a glance
- Coding index
- Codestral 2508 not benchmarked, GLM 4.6V not benchmarked.
- Widest category
- None yet: no category has been tested on both models.
- Widest single gap
- None yet: no benchmark has tested both models.
- Output price
- Both cost $0.90 per million output tokens.
- Context window
- Codestral 2508 takes 256K tokens, GLM 4.6V 131K.
Benchmark by benchmark
Every board either model has a result on, a category to a fold; bars are each result on a 0 to 100 scale. Only one model is measured on each, so no row names a leader.
CodingDirectional onlySix of these boards feed the Vibe Coding Index5 boards measured
| Benchmark | Codestral 2508 | GLM 4.6V | Leader |
|---|---|---|---|
| LiveCodeBench (Artificial Analysis run) | Not measured | 41.1% | Only GLM 4.6V measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 14.4% | Only GLM 4.6V measured |
| ALE-Bench | 137.8 | Not measured | Only Codestral 2508 measured |
| LMArena Text: coding | Not measured | 1389 | Only GLM 4.6V measured |
| LMArena Text: software and IT | Not measured | 1391 | Only GLM 4.6V measured |
| Neither model has a result on the other 34 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | Codestral 2508 | GLM 4.6V | Leader |
|---|---|---|---|
| AA Intelligence Index | Not measured | 11.2 | Only GLM 4.6V measured |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | Codestral 2508 | GLM 4.6V | Leader |
|---|---|---|---|
| τ²-Bench Telecom | Not measured | 31.6% | Only GLM 4.6V measured |
| Neither model has a result on the other 40 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index8 boards measured
| Benchmark | Codestral 2508 | GLM 4.6V | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | Not measured | 71.9% | Only GLM 4.6V measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 9.6% | Only GLM 4.6V measured |
| LMArena Text: hard prompts | Not measured | 1367 | Only GLM 4.6V measured |
| LMArena Text: expert | Not measured | 1371 | Only GLM 4.6V measured |
| LMArena Text: hard prompts in English | Not measured | 1391 | Only GLM 4.6V measured |
| LMArena Vision: diagrams | Not measured | 1182 | Only GLM 4.6V measured |
| LMArena Vision: homework | Not measured | 1155 | Only GLM 4.6V measured |
| Kagi LLM Benchmark | 32.5% | Not measured | Only Codestral 2508 measured |
| Neither model has a result on the other 14 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index2 boards measured
| Benchmark | Codestral 2508 | GLM 4.6V | Leader |
|---|---|---|---|
| AA Math Index | Not measured | 85.3 | Only GLM 4.6V measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 85.3% | Only GLM 4.6V measured |
| Neither model has a result on the other 11 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index5 boards measured
| Benchmark | Codestral 2508 | GLM 4.6V | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | Not measured | 79.9% | Only GLM 4.6V measured |
| LMArena Text: science | Not measured | 1389 | Only GLM 4.6V measured |
| LMArena Text: medicine and healthcare | Not measured | 1389 | Only GLM 4.6V measured |
| LMArena Text: legal and government | Not measured | 1393 | Only GLM 4.6V measured |
| LMArena Text: business and finance | Not measured | 1359 | Only GLM 4.6V measured |
| Neither model has a result on the other 13 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards measured
| Benchmark | Codestral 2508 | GLM 4.6V | Leader |
|---|---|---|---|
| Design Arena: websites | 1013 | Not measured | Only Codestral 2508 measured |
| Design Arena: UI components | 1017 | Not measured | Only Codestral 2508 measured |
| Design Arena: game dev | 968 | Not measured | Only Codestral 2508 measured |
| Design Arena: data viz | 1017 | Not measured | Only Codestral 2508 measured |
| Design Arena: 3D | 1020 | Not measured | Only Codestral 2508 measured |
| Design Arena: all code categories | 1007 | Not measured | Only Codestral 2508 measured |
| Neither model has a result on the other 3 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index18 boards measured
| Benchmark | Codestral 2508 | GLM 4.6V | Leader |
|---|---|---|---|
| IFBench | Not measured | 30.1% | Only GLM 4.6V measured |
| Long context reasoning (AA-LCR) | Not measured | 48.7% | Only GLM 4.6V measured |
| LMArena Text | Not measured | 1376 | Only GLM 4.6V measured |
| LMArena Text: instruction following | Not measured | 1350 | Only GLM 4.6V measured |
| LMArena Text: creative writing | Not measured | 1347 | Only GLM 4.6V measured |
| LMArena Vision | Not measured | 1164 | Only GLM 4.6V measured |
| LMArena Text: English | Not measured | 1395 | Only GLM 4.6V measured |
| LMArena Text: non-English | Not measured | 1358 | Only GLM 4.6V measured |
| LMArena Text: Chinese | Not measured | 1425 | Only GLM 4.6V measured |
| LMArena Text: Russian | Not measured | 1339 | Only GLM 4.6V measured |
| LMArena Text: multi-turn | Not measured | 1359 | Only GLM 4.6V measured |
| LMArena Text: longer queries | Not measured | 1357 | Only GLM 4.6V measured |
| LMArena Text: writing and language | Not measured | 1347 | Only GLM 4.6V measured |
| LMArena Text: entertainment and media | Not measured | 1343 | Only GLM 4.6V measured |
| LMArena Vision: English | Not measured | 1179 | Only GLM 4.6V measured |
| LMArena Vision: Chinese | Not measured | 1217 | Only GLM 4.6V measured |
| LMArena Vision: reading text | Not measured | 1171 | Only GLM 4.6V measured |
| LMArena Vision: creative writing | Not measured | 1113 | Only GLM 4.6V measured |
| Neither model has a result on the other 28 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
Same cost
Repository review
50K input + 3K output tokens
Same cost
Agent loop
200K input + 10K output tokens
Same cost
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 | Mistral Codestral 2508 | Z.ai GLM 4.6V |
|---|---|---|
| Maker | Mistral AI | Z.ai |
| Weights | No public weights listed | Open weights |
| Released | August 1, 2025 | December 8, 2025 |
| Context window | 256K | 131K |
| Input $/Mtok | $0.30 | $0.30 |
| Output $/Mtok | $0.90 | $0.90 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Codestral 2508 better than GLM 4.6V for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Codestral 2508 for a larger context window (256K against 131K tokens).
Which is cheaper, Codestral 2508 or GLM 4.6V?
Codestral 2508 costs $0.30 per million input tokens and $0.90 per million output tokens; GLM 4.6V costs $0.30 and $0.90. Cost per solved task is known for neither of them.
Which has the bigger context window, Codestral 2508 or GLM 4.6V?
Codestral 2508, with 256K tokens against 131K.
Has any benchmark tested both Codestral 2508 and GLM 4.6V?
No benchmark has tested both yet. Codestral 2508 has results on ALE-Bench, Kagi LLM Benchmark and Design Arena: websites; GLM 4.6V on LiveCodeBench (Artificial Analysis run), Terminal-Bench Hard (Artificial Analysis run) and LMArena Text: coding. Compare them on price and context instead. Data as of October 21, 2026.