Compare / head-to-head
CodestralvsQwen3.5 27B
Codestral and Qwen3.5 27B do not yet share a public benchmark, so quality cannot be compared apples-to-apples. Qwen3.5 27B is 1.6x cheaper per token. Qwen3.5 27B has the larger context window (262K tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
0
no overlap yet
Cheaper per token
Qwen3.5 27B
1.6x cheaper, input + output
Larger context
Qwen3.5 27B
262K tokens
Provider uptime (30d)
100% · —
Mistral AI · Qwen
Codestral
Mistral AI · released 2025-01-13
text
Qwen3.5 27B
Qwen
textvision
Quality
Benchmark matrix
0 shared · 1 only Codestral · 5 only Qwen3.5 27B| Benchmark | Codestral | Qwen3.5 27B | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 0 | ||||
| No public benchmark is reported for both models yet. | ||||
| Only Codestral reports · 1 | ||||
| HumanEval | 86.6% ↗ | not reported | — | — |
| Only Qwen3.5 27B reports · 5 | ||||
| SWE-bench Verified | not reported | 75% ↗ | — | — |
| GPQA Diamond | not reported | 85.5% ↗ | — | — |
| MMLU-Pro | not reported | 86.1% ↗ | — | — |
| AIME 2026 | not reported | 91.7% ↗matharena ⚠ | — | — |
| LMArena Elo | not reported | 1408.1 ↗ | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Codestral minus Qwen3.5 27B in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | Codestral | Qwen3.5 27B | Edge |
|---|---|---|---|
| Context window | 256K tokens | 262K tokens | Qwen3.5 27B |
| Max output | — | — | — |
| Input price / 1M | $0.3 ↗ | $0.086 ↗ | Qwen3.5 27B |
| Output price / 1M | $0.9 ↗ | $0.688 ↗ | Qwen3.5 27B |
| Cached input / 1M | $0.03 ↗ | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $1.2 | $0.774 | Qwen3.5 27B |
| Modalities | text | text · vision | Qwen3.5 27B |
| Released | 2025-01-13 | — | — |
| Cited benchmark scores | 1 | 5 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Codestral vs …
Models sharing the most benchmarksMore matchups
Qwen3.5 27B vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Codestral and Qwen3.5 27B on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.