whichLlmmodel
Back to Dashboard

GoogleGemini 2.5 Flash-LiteVSMistral AICodestral 22B

Analysis by:the whichllmmodel Editorial Team|Updated: June 2026

Our Take

Standardized reasoning and coding benchmarks are currently pending verification for one or both of these models. We recommend testing Gemini 2.5 Flash-Lite and Codestral 22B directly in their respective provider playgrounds to see which fits your specific prompt styles best.
Was this recommendation helpful?
Model Specs

Gemini 2.5 Flash-Lite

Benchmarks & Scores

Coding (swe-bench-verified)
41.3%

multi-file code and clearly defined tasks

Reasoning (gpqa-diamond)
62.5%

graduate-level science QA

Cost & Context

Cost (per 1M tokens)2.6x cheaper
$0.17Input: $0.10 | Output: $0.40
Context WindowLarger
1.05M tokens
Model Specs

Codestral 22B

Open SourceAPI Available

Benchmarks & Scores

Coding (human-eval)
81.1%

basic standalone code completion and simple functions

Reasoning (gpqa-diamond)
N/A

graduate-level science QA

Cost & Context

Cost (per 1M tokens)
$0.45Input: $0.30 | Output: $0.90
Context Window
32.77k tokens

Frequently Asked Questions about Gemini 2.5 Flash-Lite vs Codestral 22B

Gemini 2.5 Flash-Lite is cheaper than Codestral 22B. Gemini 2.5 Flash-Lite has a blended cost of $0.17/1M tokens, which is about 2.6x cheaper than Codestral 22B at $0.45/1M tokens.

For coding tasks, Gemini 2.5 Flash-Lite scores 41.3% on swe-bench-verified (multi-file code and clearly defined tasks), while Codestral 22B scores 81.1% on human-eval (basic standalone code completion and simple functions).

Do you want to find a model for your constraints?

Use our interactive model finder to filter LLMs by reasoning capability, coding performance, cost, and context length.

Open Model Finder