Codestral 2508 vs Gemini 3.1 Flash Lite
Codestral 2508 costs 1.7x less per output token than Gemini 3.1 Flash Lite ($0.90 vs $1.50 per million). Updated October 21, 2026; no benchmark has tested both models yet.
- Coding
- No data
- Overall
- No data
- Output $/M
- $0.90
- Coding
- No data
- Overall
- No data
- Output $/M
- $1.50
Codestral 2508 or Gemini 3.1 Flash Lite: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Codestral 2508 for output tokens 1.7x cheaper ($0.90 vs $1.50 per million).
No benchmark has tested both yet. Codestral 2508 has results on ALE-Bench, Design Arena: websites and Design Arena: UI components; Gemini 3.1 Flash Lite on SciCode, Terminal-Bench Hard (Artificial Analysis run) and WeirdML. 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.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Web design
Design Arena: websites
No call
Only Codestral 2508 has a Design Arena: websites result, 1013.
Directional only
Long documents
Listed context window
Gemini 3.1 Flash Lite
Gemini 3.1 Flash Lite takes 1.05M tokens against 256K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Codestral 2508
Codestral 2508 $0.0008, Gemini 3.1 Flash Lite $0.0010 per turn.
List prices
At a glance
- Coding index
- Codestral 2508 not benchmarked, Gemini 3.1 Flash Lite 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 Gemini 3.1 Flash Lite $1.50 per million output tokens, 1.7x apart.
- Context window
- Codestral 2508 takes 256K tokens, Gemini 3.1 Flash Lite 1.05M.
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 Index4 boards measured
| Benchmark | Codestral 2508 | Gemini 3.1 Flash Lite | Leader |
|---|---|---|---|
| SciCode | Not measured | 43.4% | Only Gemini 3.1 Flash Lite measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 24.2% | Only Gemini 3.1 Flash Lite measured |
| WeirdML | Not measured | 52.2% | Only Gemini 3.1 Flash Lite measured |
| ALE-Bench | 137.8 | Not measured | Only Codestral 2508 measured |
| Neither model has a result on the other 34 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | Codestral 2508 | Gemini 3.1 Flash Lite | Leader |
|---|---|---|---|
| Epoch Capabilities Index | Not measured | 144.3 | Only Gemini 3.1 Flash Lite measured |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index2 boards measured
| Benchmark | Codestral 2508 | Gemini 3.1 Flash Lite | Leader |
|---|---|---|---|
| τ²-Bench Telecom | Not measured | 31.3% | Only Gemini 3.1 Flash Lite measured |
| DeepResearch Bench | Not measured | 37.3% | Only Gemini 3.1 Flash Lite measured |
| Neither model has a result on the other 37 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index3 boards measured
| Benchmark | Codestral 2508 | Gemini 3.1 Flash Lite | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | Not measured | 82.2% | Only Gemini 3.1 Flash Lite measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 17.2% | Only Gemini 3.1 Flash Lite measured |
| GPQA Diamond (Epoch AI run) | Not measured | 81.8% | Only Gemini 3.1 Flash Lite measured |
| Neither model has a result on the other 18 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index2 boards measured
| Benchmark | Codestral 2508 | Gemini 3.1 Flash Lite | Leader |
|---|---|---|---|
| OTIS Mock AIME | Not measured | 80.0% | Only Gemini 3.1 Flash Lite measured |
| FrontierMath, tiers 1 to 3 | Not measured | 27.7% | Only Gemini 3.1 Flash Lite measured |
| Neither model has a result on the other 11 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards measured
| Benchmark | Codestral 2508 | Gemini 3.1 Flash Lite | Leader |
|---|---|---|---|
| Design Arena: websites | 1013 | Not measured | Only Codestral 2508 measured |
| Design Arena: UI components | 1017 | Not measured | Only Codestral 2508 measured |
| Design Arena: game dev | 968 | Not measured | Only Codestral 2508 measured |
| Design Arena: data viz | 1017 | Not measured | Only Codestral 2508 measured |
| Design Arena: 3D | 1020 | Not measured | Only Codestral 2508 measured |
| Design Arena: all code categories | 1007 | Not measured | Only Codestral 2508 measured |
| Neither model has a result on the other 3 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index4 boards measured
| Benchmark | Codestral 2508 | Gemini 3.1 Flash Lite | Leader |
|---|---|---|---|
| IFBench | Not measured | 77.2% | Only Gemini 3.1 Flash Lite measured |
| Long context reasoning (AA-LCR) | Not measured | 74.3% | Only Gemini 3.1 Flash Lite measured |
| DTBench | Not measured | 76.8% | Only Gemini 3.1 Flash Lite measured |
| LMCA | Not measured | 35.0% | Only Gemini 3.1 Flash Lite measured |
| Neither model has a result on the other 42 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 costs less
Repository review
50K input + 3K output tokens
Gemini 3.1 Flash Lite costs less
Agent loop
200K input + 10K output tokens
Gemini 3.1 Flash Lite 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 | Google Gemini 3.1 Flash Lite |
|---|---|---|
| Maker | Mistral AI | |
| Weights | No public weights listed | No public weights listed |
| Released | August 1, 2025 | May 7, 2026 |
| Context window | 256K | 1.05M |
| Input $/Mtok | $0.30 | $0.25 |
| Output $/Mtok | $0.90 | $1.50 |
| 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 Gemini 3.1 Flash Lite for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Codestral 2508 for output tokens 1.7x cheaper ($0.90 vs $1.50 per million).
Which is cheaper, Codestral 2508 or Gemini 3.1 Flash Lite?
Codestral 2508 costs $0.30 per million input tokens and $0.90 per million output tokens; Gemini 3.1 Flash Lite costs $0.25 and $1.50. Cost per solved task is known for neither of them.
Which has the bigger context window, Codestral 2508 or Gemini 3.1 Flash Lite?
Gemini 3.1 Flash Lite, with 1.05M tokens against 256K.
Has any benchmark tested both Codestral 2508 and Gemini 3.1 Flash Lite?
No benchmark has tested both yet. Codestral 2508 has results on ALE-Bench, Design Arena: websites and Design Arena: UI components; Gemini 3.1 Flash Lite on SciCode, Terminal-Bench Hard (Artificial Analysis run) and WeirdML. Compare them on price and context instead. Data as of October 21, 2026.