Codestral 2508 vs Gemma 2 27B
Updated October 21, 2026. No benchmark has tested both models yet. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
- Coding
- No data
- Overall
- No data
- Output $/M
- $0.90
- Coding
- No data
- Overall
- No data
- Output $/M
- $0.65
Decision reading
Neither model has a coding score yet, so the two cannot be ranked on coding.
Codestral 2508 has the edge where the context window is larger, 256K against 8K tokens.
No benchmark has tested both yet. Codestral 2508 has results on ALE-Bench, Design Arena: websites and Design Arena: UI components; Gemma 2 27B on LMArena Text: coding, LMArena Text: software and IT and Epoch Capabilities 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.
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
Codestral 2508
Codestral 2508 takes 256K tokens against 8K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Codestral 2508
Codestral 2508 $0.0008, Gemma 2 27B $0.0010 per turn.
List prices
At a glance
- Coding index
- Codestral 2508 not benchmarked, Gemma 2 27B 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 Gemma 2 27B $0.65 per million output tokens, 1.4x apart.
- Context window
- Codestral 2508 takes 256K tokens, Gemma 2 27B 8K.
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 Index3 boards measured
| Benchmark | Codestral 2508 | Gemma 2 27B | Leader |
|---|---|---|---|
| ALE-Bench | 137.8 | Not measured | Only Codestral 2508 measured |
| LMArena Text: coding | Not measured | 1211 | Only Gemma 2 27B measured |
| LMArena Text: software and IT | Not measured | 1228 | Only Gemma 2 27B measured |
| Neither model has a result on the other 35 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | Codestral 2508 | Gemma 2 27B | Leader |
|---|---|---|---|
| Epoch Capabilities Index | Not measured | 122.1 | Only Gemma 2 27B measured |
| Neither model has a result on the other 1 board here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index4 boards measured
| Benchmark | Codestral 2508 | Gemma 2 27B | Leader |
|---|---|---|---|
| GPQA Diamond (Epoch AI run) | Not measured | 36.5% | Only Gemma 2 27B measured |
| LMArena Text: hard prompts | Not measured | 1198 | Only Gemma 2 27B measured |
| LMArena Text: expert | Not measured | 1171 | Only Gemma 2 27B measured |
| LMArena Text: hard prompts in English | Not measured | 1206 | Only Gemma 2 27B measured |
| Neither model has a result on the other 17 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index4 boards measured
| Benchmark | Codestral 2508 | Gemma 2 27B | Leader |
|---|---|---|---|
| OTIS Mock AIME | Not measured | 1.4% | Only Gemma 2 27B measured |
| MATH level 5 | Not measured | 27.9% | Only Gemma 2 27B measured |
| LMArena Text: math | Not measured | 1212 | Only Gemma 2 27B measured |
| LMArena Text: mathematical work | Not measured | 1221 | Only Gemma 2 27B measured |
| Neither model has a result on the other 9 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index6 boards measured
| Benchmark | Codestral 2508 | Gemma 2 27B | Leader |
|---|---|---|---|
| LegalBench (Vals AI) | Not measured | 68.0% | Only Gemma 2 27B measured |
| MMLU | Not measured | 75.7% | Only Gemma 2 27B measured |
| LMArena Text: science | Not measured | 1228 | Only Gemma 2 27B measured |
| LMArena Text: medicine and healthcare | Not measured | 1198 | Only Gemma 2 27B measured |
| LMArena Text: legal and government | Not measured | 1241 | Only Gemma 2 27B measured |
| LMArena Text: business and finance | Not measured | 1208 | Only Gemma 2 27B 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 | Gemma 2 27B | 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 index19 boards measured
| Benchmark | Codestral 2508 | Gemma 2 27B | Leader |
|---|---|---|---|
| DTBench | Not measured | 48.0% | Only Gemma 2 27B measured |
| LMCA | Not measured | 7.1% | Only Gemma 2 27B measured |
| LMArena Text | Not measured | 1231 | Only Gemma 2 27B measured |
| LMArena Text: instruction following | Not measured | 1206 | Only Gemma 2 27B measured |
| LMArena Text: creative writing | Not measured | 1240 | Only Gemma 2 27B measured |
| LMArena Text: English | Not measured | 1242 | Only Gemma 2 27B measured |
| LMArena Text: non-English | Not measured | 1217 | Only Gemma 2 27B measured |
| LMArena Text: Chinese | Not measured | 1221 | Only Gemma 2 27B measured |
| LMArena Text: German | Not measured | 1209 | Only Gemma 2 27B measured |
| LMArena Text: Japanese | Not measured | 1175 | Only Gemma 2 27B measured |
| LMArena Text: Korean | Not measured | 1174 | Only Gemma 2 27B measured |
| LMArena Text: French | Not measured | 1248 | Only Gemma 2 27B measured |
| LMArena Text: Spanish | Not measured | 1228 | Only Gemma 2 27B measured |
| LMArena Text: Russian | Not measured | 1234 | Only Gemma 2 27B measured |
| LMArena Text: Polish | Not measured | 1277 | Only Gemma 2 27B measured |
| LMArena Text: multi-turn | Not measured | 1224 | Only Gemma 2 27B measured |
| LMArena Text: longer queries | Not measured | 1230 | Only Gemma 2 27B measured |
| LMArena Text: writing and language | Not measured | 1249 | Only Gemma 2 27B measured |
| LMArena Text: entertainment and media | Not measured | 1212 | Only Gemma 2 27B measured |
| Neither model has a result on the other 27 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
Codestral 2508 costs less
Agent loop
200K input + 10K output tokens
Codestral 2508 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 Gemma 2 27B |
|---|---|---|
| Maker | Mistral AI | |
| Weights | No public weights listed | Open weights |
| Released | August 1, 2025 | July 13, 2024 |
| Context window | 256K | 8K |
| Input $/Mtok | $0.30 | $0.65 |
| Output $/Mtok | $0.90 | $0.65 |
| 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 Gemma 2 27B for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Codestral 2508 has the edge where the context window is larger, 256K against 8K tokens.
Which is cheaper, Codestral 2508 or Gemma 2 27B?
Codestral 2508 costs $0.30 per million input tokens and $0.90 per million output tokens; Gemma 2 27B costs $0.65 and $0.65. Cost per solved task is known for neither of them.
Which has the bigger context window, Codestral 2508 or Gemma 2 27B?
Codestral 2508, with 256K tokens against 8K.
Has any benchmark tested both Codestral 2508 and Gemma 2 27B?
No benchmark has tested both yet. Codestral 2508 has results on ALE-Bench, Design Arena: websites and Design Arena: UI components; Gemma 2 27B on LMArena Text: coding, LMArena Text: software and IT and Epoch Capabilities Index. Compare them on price and context instead. Data as of October 21, 2026.