Model Comparison 2026

Codestral vs Qwen3 235B A22B

Codestral
Mistral · Budget · Proprietary
$0.48/1M · 256K ctx
Qwen3 235B A22B
Alibaba (Qwen) · Budget · Open weights
$0.09/1M · 262K ctx

Community Vote

Pick a winner in each dimension — change your vote anytime.

Output Quality
Correctness and depth of what it produces
Agentic Ability
Tool calls, instruction-following, and multi-step tasks
Speed
Tokens per second and time-to-first-token
Value for $
How much capability you get per dollar
Reliability
Consistent results — fewer refusals, loops, and format breaks

Specs & Pricing, Side by Side

Spec
Codestral
Qwen3 235B
Maker
Mistral
Alibaba (Qwen)
Blended price / 1M
$0.48
$0.09
Input / output
$0.30 in · $0.90 out / 1M tokens
$0.09 in · $0.10 out / 1M tokens
Context window
256K
262K
Open weights
No
Yes
Tool use
Yes
Yes
Reasoning
No
No
Output Quality
6.8
8.0
Agentic Ability
6.5
8.0
Speed
9.5
8.2
Value for $
8.9
10.0
Reliability
8.8
8.8

Pricing and capabilities synced from the OpenRouter catalogue. Scores are editorial (0–10).

Verdict: Codestral or Qwen3 235B?

Updated 2026-06-22

Choose Codestral if you want fast completions and lightweight code edits. Choose Qwen3 235B A22B if you want self-hosted or ultra-cheap open-weight agents.

In our editorial scoring, Qwen3 235B A22B leads in 3 of five dimensions (output quality, agentic ability and value for $), while Codestral leads in 1. On price, Codestral runs about $0.48 per 1M tokens (blended) and is proprietary; Qwen3 235B A22B is about $0.09 and open-weight.

Where Codestral falls short
  • Not for deep agentic planning
  • Quality below the larger coders
Full Codestral breakdown →
Where Qwen3 235B falls short
  • Behind frontier models on quality
  • Needs real GPUs to self-host well
Full Qwen3 235B breakdown →

The model is half the story — the agent is the other half

The model picks the moves; the agent runs the loop, the tools, and the guardrails. Once you've chosen a model, see which agent gets the most out of it.

Compare AI agents →

Related comparisons

Haiku 4.5 vs Qwen3 235BHaiku 4.5 vs CodestralDeepSeek V4 Flash vs Qwen3 235BCodestral vs DeepSeek V4 FlashGPT-5.4 Mini vs Qwen3 235BCodestral vs GPT-5.4 MiniFlash Lite vs Qwen3 235BLlama 4 Maverick vs Qwen3 235B