Codestral 2508 vs Gemma 4 26B A4B
Updated October 21, 2026. 1 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Neither model has a coding score yet, so the two cannot be ranked on coding.
Codestral 2508 has the edge where the benchmark that matters is ALE-Bench, where it leads.
- Shared results
- 1
- Codestral 2508 only
- 6
- Gemma 4 26B A4B only
- 53
- Like-for-like categories
- 1 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
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
Intelligence
AA Intelligence Index
No call
Only Gemma 4 26B A4B has a AA Intelligence Index result, 16.7.
Directional only
Agentic work
AA Agentic Index
No call
Only Gemma 4 26B A4B has a AA Agentic Index result, 2.9.
Directional only
Web design
Design Arena: websites
No call
Only Codestral 2508 has a Design Arena: websites result, 1013.
Directional only
Long documents
Listed context window
Gemma 4 26B A4B
Gemma 4 26B A4B takes 262K tokens against 256K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Gemma 4 26B A4B
Codestral 2508 $0.0008, Gemma 4 26B A4B $0.0004 per turn.
List prices
At a glance
- Coding index
- Codestral 2508 not benchmarked, Gemma 4 26B A4B not benchmarked.
- Widest category
- Coding, 26.3 points apart on average over 1 shared benchmark.
- Widest single gap
- ALE-Bench: Codestral 2508 137.8 against Gemma 4 26B A4B 927.2, 26.3 points apart on a 0 to 100 scale.
- Output price
- Codestral 2508 $0.90 against Gemma 4 26B A4B $0.60 per million output tokens, 1.5x apart.
- Context window
- Codestral 2508 takes 256K tokens, Gemma 4 26B A4B 262K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Codestral 2508 | Bars | Gemma 4 26B A4B | Ties |
|---|---|---|---|---|
| Coding | 0 | 1 | ||
| All shared boards | 0 | 1 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index01
| Benchmark | Codestral 2508 | Gemma 4 26B A4B | Leader |
|---|---|---|---|
| LMArena WebDev | Not measured | 1360 | Only Gemma 4 26B A4B measured |
| AA Coding Index | Not measured | 39.3 | Only Gemma 4 26B A4B measured |
| SciCode | Not measured | 40.0% | Only Gemma 4 26B A4B measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 25.0% | Only Gemma 4 26B A4B measured |
| WeirdML | Not measured | 35.2% | Only Gemma 4 26B A4B measured |
| ALE-Bench | 137.8 | 927.2 | Gemma 4 26B A4B |
| LMArena Text: coding | Not measured | 1446 | Only Gemma 4 26B A4B measured |
| LMArena Text: software and IT | Not measured | 1454 | Only Gemma 4 26B A4B measured |
| LMArena WebDev: React | Not measured | 1351 | Only Gemma 4 26B A4B measured |
| LMArena WebDev: HTML | Not measured | 1362 | Only Gemma 4 26B A4B measured |
| Neither model has a result on the other 28 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Codestral 2508 | Gemma 4 26B A4B | Leader |
|---|---|---|---|
| AA Intelligence Index | Not measured | 16.7 | Only Gemma 4 26B A4B measured |
| Epoch Capabilities Index | Not measured | 141.9 | Only Gemma 4 26B A4B measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Codestral 2508 | Gemma 4 26B A4B | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 2.9 | Only Gemma 4 26B A4B measured |
| τ²-Bench Telecom | Not measured | 43.6% | Only Gemma 4 26B A4B measured |
| Neither model has a result on the other 37 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Codestral 2508 | Gemma 4 26B A4B | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | Not measured | 79.2% | Only Gemma 4 26B A4B measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 19.3% | Only Gemma 4 26B A4B measured |
| GPQA Diamond (Epoch AI run) | Not measured | 73.2% | Only Gemma 4 26B A4B measured |
| LMArena Text: hard prompts | Not measured | 1438 | Only Gemma 4 26B A4B measured |
| LMArena Text: expert | Not measured | 1447 | Only Gemma 4 26B A4B measured |
| LMArena Text: hard prompts in English | Not measured | 1448 | Only Gemma 4 26B A4B measured |
| LMArena Vision: diagrams | Not measured | 1264 | Only Gemma 4 26B A4B measured |
| LMArena Vision: homework | Not measured | 1293 | Only Gemma 4 26B A4B measured |
| Neither model has a result on the other 13 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
| Benchmark | Codestral 2508 | Gemma 4 26B A4B | Leader |
|---|---|---|---|
| OTIS Mock AIME | Not measured | 82.2% | Only Gemma 4 26B A4B measured |
| LMArena Text: math | Not measured | 1470 | Only Gemma 4 26B A4B measured |
| LMArena Text: mathematical work | Not measured | 1475 | Only Gemma 4 26B A4B measured |
| Neither model has a result on the other 10 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
| Benchmark | Codestral 2508 | Gemma 4 26B A4B | Leader |
|---|---|---|---|
| LMArena Text: science | Not measured | 1446 | Only Gemma 4 26B A4B measured |
| LMArena Text: medicine and healthcare | Not measured | 1428 | Only Gemma 4 26B A4B measured |
| LMArena Text: legal and government | Not measured | 1457 | Only Gemma 4 26B A4B measured |
| LMArena Text: business and finance | Not measured | 1429 | Only Gemma 4 26B A4B measured |
| Neither model has a result on the other 13 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | Codestral 2508 | Gemma 4 26B A4B | 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 index25 boards, none shared
| Benchmark | Codestral 2508 | Gemma 4 26B A4B | Leader |
|---|---|---|---|
| IFBench | Not measured | 72.4% | Only Gemma 4 26B A4B measured |
| Long context reasoning (AA-LCR) | Not measured | 65.7% | Only Gemma 4 26B A4B measured |
| DTBench | Not measured | 74.9% | Only Gemma 4 26B A4B measured |
| LMCA | Not measured | 29.7% | Only Gemma 4 26B A4B measured |
| LMArena Text | Not measured | 1434 | Only Gemma 4 26B A4B measured |
| LMArena Text: instruction following | Not measured | 1420 | Only Gemma 4 26B A4B measured |
| LMArena Text: creative writing | Not measured | 1400 | Only Gemma 4 26B A4B measured |
| LMArena Vision | Not measured | 1260 | Only Gemma 4 26B A4B measured |
| LMArena Text: English | Not measured | 1444 | Only Gemma 4 26B A4B measured |
| LMArena Text: non-English | Not measured | 1421 | Only Gemma 4 26B A4B measured |
| LMArena Text: Chinese | Not measured | 1495 | Only Gemma 4 26B A4B measured |
| LMArena Text: French | Not measured | 1460 | Only Gemma 4 26B A4B measured |
| LMArena Text: Spanish | Not measured | 1415 | Only Gemma 4 26B A4B measured |
| LMArena Text: Russian | Not measured | 1434 | Only Gemma 4 26B A4B measured |
| LMArena Text: multi-turn | Not measured | 1441 | Only Gemma 4 26B A4B measured |
| LMArena Text: longer queries | Not measured | 1427 | Only Gemma 4 26B A4B measured |
| LMArena Text: writing and language | Not measured | 1405 | Only Gemma 4 26B A4B measured |
| LMArena Text: entertainment and media | Not measured | 1403 | Only Gemma 4 26B A4B measured |
| LMArena Vision: English | Not measured | 1256 | Only Gemma 4 26B A4B measured |
| LMArena Vision: Chinese | Not measured | 1312 | Only Gemma 4 26B A4B measured |
| LMArena Vision: reading text | Not measured | 1268 | Only Gemma 4 26B A4B measured |
| LMArena Vision: humor | Not measured | 1272 | Only Gemma 4 26B A4B measured |
| LMArena Vision: captioning | Not measured | 1297 | Only Gemma 4 26B A4B measured |
| LMArena Vision: recognizing things | Not measured | 1191 | Only Gemma 4 26B A4B measured |
| LMArena Vision: creative writing | Not measured | 1256 | Only Gemma 4 26B A4B measured |
| Neither model has a result on the other 21 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Codestral 2508 | Gemma 4 26B A4B | Leader |
|---|---|---|---|
| Neither model has a result on 5 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
Gemma 4 26B A4B costs less
Repository review
50K input + 3K output tokens
Gemma 4 26B A4B costs less
Agent loop
200K input + 10K output tokens
Gemma 4 26B A4B 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 4 26B A4B |
|---|---|---|
| Maker | Mistral AI | |
| Weights | No public weights listed | Open weights |
| Released | August 1, 2025 | April 3, 2026 |
| Context window | 256K | 262K |
| Input $/Mtok | $0.30 | $0.15 |
| Output $/Mtok | $0.90 | $0.60 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 1 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Codestral 2508 better than Gemma 4 26B A4B for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Codestral 2508 has the edge where the benchmark that matters is ALE-Bench, where it leads.
Which is cheaper, Codestral 2508 or Gemma 4 26B A4B?
Codestral 2508 costs $0.30 per million input tokens and $0.90 per million output tokens; Gemma 4 26B A4B costs $0.15 and $0.60. Cost per solved task is known for neither of them.
Which has the bigger context window, Codestral 2508 or Gemma 4 26B A4B?
Gemma 4 26B A4B, with 262K tokens against 256K.
How many benchmarks is the Codestral 2508 vs Gemma 4 26B A4B comparison based on?
1 benchmarks have a result for both models as of October 21, 2026. Codestral 2508's coding index rests on 0 independent benchmarks and Gemma 4 26B A4B's on 1. Where only one model has a result, the page says so instead of naming a winner.