Enter opens the highlighted result. Esc closes.

Codestral 2508 vs Qwen3 VL 30B A3B Thinking

Codestral 2508 and Qwen3 VL 30B A3B Thinking cost about the same per output token ($0.90 vs $1.00 per million). Updated October 22, 2026; no benchmark has tested both models yet.

Replace Codestral 2508 Replace Qwen3 VL 30B A3B Thinking
Codestral 2508Mistral AI
Coding
No data
Overall
No data
Output $/M
$0.90
Qwen3 VL 30B A3B ThinkingQwen
Coding
No data
Overall
No data
Output $/M
$1.00
vs $0.90 vs $1.00 per 1M output tokens. Codestral 2508 is 1.1x cheaper.

Codestral 2508 or Qwen3 VL 30B A3B Thinking: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick Codestral 2508 for output tokens 1.1x cheaper ($0.90 vs $1.00 per million).

Model ACodestral 2508Mistral AINot benchmarkedNo coding benchmarkNo cost per solved taskModel BQwen3 VL 30B A3B ThinkingQwenNot benchmarkedNo coding benchmarkNo cost per solved task

No benchmark has tested both yet. Codestral 2508 has results on ALE-Bench, Kagi LLM Benchmark and Design Arena: websites; Qwen3 VL 30B A3B Thinking on AA Intelligence Index. 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.

At a glance

Coding index
Codestral 2508 not benchmarked, Qwen3 VL 30B A3B Thinking 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
Codestral 2508 $0.90 against Qwen3 VL 30B A3B Thinking $1.00 per million output tokens, 1.1x apart.
Context window
Codestral 2508 takes 256K tokens, Qwen3 VL 30B A3B Thinking 262K.

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 Index1 board measured
Coding benchmarks for Codestral 2508 and Qwen3 VL 30B A3B Thinking
BenchmarkCodestral 2508Qwen3 VL 30B A3B ThinkingLeader
ALE-Bench137.8Not measuredOnly Codestral 2508 measured
Neither model has a result on the other 38 boards here
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
Intelligence benchmarks for Codestral 2508 and Qwen3 VL 30B A3B Thinking
BenchmarkCodestral 2508Qwen3 VL 30B A3B ThinkingLeader
AA Intelligence IndexNot measured9.5Only Qwen3 VL 30B A3B Thinking measured
Neither model has a result on the other 1 board here
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
Reasoning benchmarks for Codestral 2508 and Qwen3 VL 30B A3B Thinking
BenchmarkCodestral 2508Qwen3 VL 30B A3B ThinkingLeader
Kagi LLM Benchmark32.5%Not measuredOnly Codestral 2508 measured
Neither model has a result on the other 21 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards measured
Web design benchmarks for Codestral 2508 and Qwen3 VL 30B A3B Thinking
BenchmarkCodestral 2508Qwen3 VL 30B A3B ThinkingLeader
Design Arena: websites1012Not measuredOnly Codestral 2508 measured
Design Arena: UI components1014Not measuredOnly Codestral 2508 measured
Design Arena: game dev967Not measuredOnly Codestral 2508 measured
Design Arena: data viz1017Not measuredOnly Codestral 2508 measured
Design Arena: 3D1019Not measuredOnly Codestral 2508 measured
Design Arena: all code categories1007Not measuredOnly Codestral 2508 measured
Neither model has a result on the other 3 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

Codestral 2508$0.0008Fits in one request
Qwen3 VL 30B A3B Thinking$0.0008Fits in one request

Codestral 2508 costs less

Repository review

50K input + 3K output tokens

Codestral 2508$0.018Fits in one request
Qwen3 VL 30B A3B Thinking$0.018Fits in one request

Qwen3 VL 30B A3B Thinking costs less

Agent loop

200K input + 10K output tokens

Codestral 2508$0.069Fits in one request
Qwen3 VL 30B A3B Thinking$0.068Fits in one request

Qwen3 VL 30B A3B Thinking 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.

Specifications of Codestral 2508 and Qwen3 VL 30B A3B Thinking
SpecificationMistral Codestral 2508Qwen3 VL 30B A3B Thinking
MakerMistral AIQwen
WeightsNo public weights listedOpen weights
ReleasedAugust 1, 2025October 6, 2025
Context window256K262K
Input $/Mtok$0.30$0.29
Output $/Mtok$0.90$1.00
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Codestral 2508 better than Qwen3 VL 30B A3B Thinking for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Codestral 2508 for output tokens 1.1x cheaper ($0.90 vs $1.00 per million).

Which is cheaper, Codestral 2508 or Qwen3 VL 30B A3B Thinking?

Codestral 2508 costs $0.30 per million input tokens and $0.90 per million output tokens; Qwen3 VL 30B A3B Thinking costs $0.29 and $1.00. Cost per solved task is known for neither of them.

Which has the bigger context window, Codestral 2508 or Qwen3 VL 30B A3B Thinking?

Qwen3 VL 30B A3B Thinking, with 262K tokens against 256K.

Has any benchmark tested both Codestral 2508 and Qwen3 VL 30B A3B Thinking?

No benchmark has tested both yet. Codestral 2508 has results on ALE-Bench, Kagi LLM Benchmark and Design Arena: websites; Qwen3 VL 30B A3B Thinking on AA Intelligence Index. Compare them on price and context instead. Data as of October 22, 2026.

Compare next