Codestral 2508 vs Qwen3 30B A3B
Qwen3 30B A3B costs 1.8x less per output token than Codestral 2508 ($0.50 vs $0.90 per million). Updated October 21, 2026; 5 benchmarks have a result for both.
Codestral 2508 or Qwen3 30B A3B: 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 41K tokens).
- Shared results
- 5
- Codestral 2508 only
- 3
- Qwen3 30B A3B only
- 47
- Like-for-like categories
- 1 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
No call
Only Qwen3 30B A3B has a AA Intelligence Index result, 7.6.
Directional only
Web design
Design Arena: websites
Codestral 2508
Codestral 2508 leads, 1013 against 955.
Same board, both measured
Long documents
Listed context window
Codestral 2508
Codestral 2508 takes 256K tokens against 41K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen3 30B A3B
Codestral 2508 $0.0008, Qwen3 30B A3B $0.0004 per turn.
List prices
At a glance
- Coding index
- Codestral 2508 not benchmarked, Qwen3 30B A3B not benchmarked.
- Widest category
- Web design, 7.8 points apart on average over 5 shared benchmarks.
- Widest single gap
- Design Arena: UI components: Codestral 2508 1017 against Qwen3 30B A3B 946, 8.9 points apart on a 0 to 100 scale.
- Output price
- Codestral 2508 $0.90 against Qwen3 30B A3B $0.50 per million output tokens, 1.8x apart.
- Context window
- Codestral 2508 takes 256K tokens, Qwen3 30B A3B 41K.
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 | Codestral 2508 | Bars | Qwen3 30B A3B | Ties |
|---|---|---|---|---|
| Web design | 5 | 0 | ||
| All shared boards | 5 | 0 |
CodingDirectional onlySix of these boards feed the Vibe Coding Index6 boards, none shared
| Benchmark | Codestral 2508 | Qwen3 30B A3B | Leader |
|---|---|---|---|
| LiveCodeBench (Artificial Analysis run) | Not measured | 50.6% | Only Qwen3 30B A3B measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 6.8% | Only Qwen3 30B A3B measured |
| WeirdML | Not measured | 29.8% | Only Qwen3 30B A3B measured |
| ALE-Bench | 137.8 | Not measured | Only Codestral 2508 measured |
| LMArena Text: coding | Not measured | 1337 | Only Qwen3 30B A3B measured |
| LMArena Text: software and IT | Not measured | 1340 | Only Qwen3 30B A3B measured |
| Neither model has a result on the other 33 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Codestral 2508 | Qwen3 30B A3B | Leader |
|---|---|---|---|
| AA Intelligence Index | Not measured | 7.6 | Only Qwen3 30B A3B measured |
| Epoch Capabilities Index | Not measured | 137.3 | Only Qwen3 30B A3B measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Codestral 2508 | Qwen3 30B A3B | Leader |
|---|---|---|---|
| τ²-Bench Telecom | Not measured | 26.0% | Only Qwen3 30B A3B measured |
| Neither model has a result on the other 40 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | Codestral 2508 | Qwen3 30B A3B | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | Not measured | 61.6% | Only Qwen3 30B A3B measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 6.2% | Only Qwen3 30B A3B measured |
| GPQA Diamond (Epoch AI run) | Not measured | 61.7% | Only Qwen3 30B A3B measured |
| LMArena Text: hard prompts | Not measured | 1314 | Only Qwen3 30B A3B measured |
| LMArena Text: expert | Not measured | 1314 | Only Qwen3 30B A3B measured |
| LMArena Text: hard prompts in English | Not measured | 1329 | Only Qwen3 30B A3B measured |
| Kagi LLM Benchmark | 32.5% | Not measured | Only Codestral 2508 measured |
| Neither model has a result on the other 15 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | Codestral 2508 | Qwen3 30B A3B | Leader |
|---|---|---|---|
| AA Math Index | Not measured | 72.3 | Only Qwen3 30B A3B measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 72.3% | Only Qwen3 30B A3B measured |
| OTIS Mock AIME | Not measured | 62.8% | Only Qwen3 30B A3B measured |
| LMArena Text: math | Not measured | 1355 | Only Qwen3 30B A3B measured |
| LMArena Text: mathematical work | Not measured | 1363 | Only Qwen3 30B A3B measured |
| Neither model has a result on the other 8 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | Codestral 2508 | Qwen3 30B A3B | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | Not measured | 77.7% | Only Qwen3 30B A3B measured |
| LMArena Text: science | Not measured | 1321 | Only Qwen3 30B A3B measured |
| LMArena Text: medicine and healthcare | Not measured | 1318 | Only Qwen3 30B A3B measured |
| LMArena Text: legal and government | Not measured | 1314 | Only Qwen3 30B A3B measured |
| LMArena Text: business and finance | Not measured | 1309 | Only Qwen3 30B A3B measured |
| Neither model has a result on the other 13 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Codestral 2508 | Qwen3 30B A3B | Leader |
|---|---|---|---|
| Design Arena: websites | 1013 | 955 | Codestral 2508 |
| Design Arena: UI components | 1017 | 946 | Codestral 2508 |
| Design Arena: game dev | 968 | 899 | Codestral 2508 |
| Design Arena: data viz | 1017 | 967 | Codestral 2508 |
| Design Arena: 3D | 1020 | Not measured | Only Codestral 2508 measured |
| Design Arena: all code categories | 1007 | 942 | Codestral 2508 |
| Neither model has a result on the other 3 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index23 boards, none shared
| Benchmark | Codestral 2508 | Qwen3 30B A3B | Leader |
|---|---|---|---|
| IFBench | Not measured | 41.5% | Only Qwen3 30B A3B measured |
| Long context reasoning (AA-LCR) | Not measured | 0.0% | Only Qwen3 30B A3B measured |
| DTBench | Not measured | 60.3% | Only Qwen3 30B A3B measured |
| LMCA | Not measured | 15.8% | Only Qwen3 30B A3B measured |
| Fiction.LiveBench | Not measured | 40.6% | Only Qwen3 30B A3B measured |
| Creative writing (Lech Mazur) | Not measured | 75.3% | Only Qwen3 30B A3B measured |
| LMArena Text | Not measured | 1317 | Only Qwen3 30B A3B measured |
| LMArena Text: instruction following | Not measured | 1283 | Only Qwen3 30B A3B measured |
| LMArena Text: creative writing | Not measured | 1271 | Only Qwen3 30B A3B measured |
| LMArena Text: English | Not measured | 1335 | Only Qwen3 30B A3B measured |
| LMArena Text: non-English | Not measured | 1295 | Only Qwen3 30B A3B measured |
| LMArena Text: Chinese | Not measured | 1347 | Only Qwen3 30B A3B measured |
| LMArena Text: German | Not measured | 1307 | Only Qwen3 30B A3B measured |
| LMArena Text: Japanese | Not measured | 1254 | Only Qwen3 30B A3B measured |
| LMArena Text: Korean | Not measured | 1261 | Only Qwen3 30B A3B measured |
| LMArena Text: French | Not measured | 1352 | Only Qwen3 30B A3B measured |
| LMArena Text: Spanish | Not measured | 1317 | Only Qwen3 30B A3B measured |
| LMArena Text: Russian | Not measured | 1291 | Only Qwen3 30B A3B measured |
| LMArena Text: Polish | Not measured | 1299 | Only Qwen3 30B A3B measured |
| LMArena Text: multi-turn | Not measured | 1307 | Only Qwen3 30B A3B measured |
| LMArena Text: longer queries | Not measured | 1312 | Only Qwen3 30B A3B measured |
| LMArena Text: writing and language | Not measured | 1290 | Only Qwen3 30B A3B measured |
| LMArena Text: entertainment and media | Not measured | 1258 | Only Qwen3 30B A3B measured |
| Neither model has a result on the other 23 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Codestral 2508 | Qwen3 30B A3B | 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
Qwen3 30B A3B costs less
Repository review
50K input + 3K output tokens
Qwen3 30B A3B costs less
Agent loop
200K input + 10K output tokens
Qwen3 30B A3B 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 | Mistral Codestral 2508 | Qwen3 30B A3B |
|---|---|---|
| Maker | Mistral AI | Qwen |
| Weights | No public weights listed | Open weights |
| Released | August 1, 2025 | April 28, 2025 |
| Context window | 256K | 41K |
| Input $/Mtok | $0.30 | $0.12 |
| Output $/Mtok | $0.90 | $0.50 |
| 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 Qwen3 30B A3B 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 41K tokens).
Which is cheaper, Codestral 2508 or Qwen3 30B A3B?
Codestral 2508 costs $0.30 per million input tokens and $0.90 per million output tokens; Qwen3 30B A3B costs $0.12 and $0.50. Cost per solved task is known for neither of them.
Which has the bigger context window, Codestral 2508 or Qwen3 30B A3B?
Codestral 2508, with 256K tokens against 41K.
How many benchmarks is the Codestral 2508 vs Qwen3 30B A3B comparison based on?
5 benchmarks have a result for both models as of October 21, 2026. Codestral 2508's coding index rests on 0 independent benchmarks and Qwen3 30B A3B's on 0. Where only one model has a result, the page says so instead of naming a winner.