Nova Pro 1.0 vs Codestral 2508
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.
Nova Pro 1.0 has the edge where the context window is larger, 300K against 256K tokens, and where the benchmark that matters is Design Arena: websites, where it leads.
- Shared results
- 1
- Nova Pro 1.0 only
- 41
- Codestral 2508 only
- 6
- 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 Nova Pro 1.0 has a AA Intelligence Index result, 7.0.
Directional only
Web design
Design Arena: websites
Codestral 2508
Codestral 2508 leads, 1013 against 796.
Same board, both measured
Long documents
Listed context window
Nova Pro 1.0
Nova Pro 1.0 takes 300K tokens against 256K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Codestral 2508
Nova Pro 1.0 $0.0024, Codestral 2508 $0.0008 per turn.
List prices
At a glance
- Coding index
- Nova Pro 1.0 not benchmarked, Codestral 2508 not benchmarked.
- Widest category
- Web design, 27.1 points apart on average over 1 shared benchmark.
- Widest single gap
- Design Arena: websites: Nova Pro 1.0 796 against Codestral 2508 1013, 27.1 points apart on a 0 to 100 scale.
- Output price
- Nova Pro 1.0 $3.20 against Codestral 2508 $0.90 per million output tokens, 3.6x apart.
- Context window
- Nova Pro 1.0 takes 300K tokens, Codestral 2508 256K.
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 | Nova Pro 1.0 | Bars | Codestral 2508 | Ties |
|---|---|---|---|---|
| Web design | 0 | 1 | ||
| All shared boards | 0 | 1 |
CodingDirectional onlySix of these boards feed the Vibe Coding Index5 boards, none shared
| Benchmark | Nova Pro 1.0 | Codestral 2508 | Leader |
|---|---|---|---|
| LiveCodeBench (Artificial Analysis run) | 23.3% | Not measured | Only Nova Pro 1.0 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 6.1% | Not measured | Only Nova Pro 1.0 measured |
| ALE-Bench | Not measured | 137.8 | Only Codestral 2508 measured |
| LMArena Text: coding | 1270 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: software and IT | 1271 | Not measured | Only Nova Pro 1.0 measured |
| Neither model has a result on the other 33 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Nova Pro 1.0 | Codestral 2508 | Leader |
|---|---|---|---|
| AA Intelligence Index | 7.0 | Not measured | Only Nova Pro 1.0 measured |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Nova Pro 1.0 | Codestral 2508 | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 14.0% | Not measured | Only Nova Pro 1.0 measured |
| Neither model has a result on the other 38 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | Nova Pro 1.0 | Codestral 2508 | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 49.9% | Not measured | Only Nova Pro 1.0 measured |
| Humanity's Last Exam (Artificial Analysis run) | 3.2% | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: hard prompts | 1246 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: expert | 1211 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: hard prompts in English | 1259 | Not measured | Only Nova Pro 1.0 measured |
| Neither model has a result on the other 16 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
| Benchmark | Nova Pro 1.0 | Codestral 2508 | Leader |
|---|---|---|---|
| AA Math Index | 7.0 | Not measured | Only Nova Pro 1.0 measured |
| AIME 2025 (Artificial Analysis run) | 7.0% | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: math | 1252 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: mathematical work | 1261 | Not measured | Only Nova Pro 1.0 measured |
| Neither model has a result on the other 9 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | Nova Pro 1.0 | Codestral 2508 | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 69.1% | Not measured | Only Nova Pro 1.0 measured |
| MMLU | 82.0% | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: science | 1255 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: medicine and healthcare | 1260 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: legal and government | 1281 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: business and finance | 1229 | Not measured | Only Nova Pro 1.0 measured |
| Neither model has a result on the other 11 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Nova Pro 1.0 | Codestral 2508 | Leader |
|---|---|---|---|
| Design Arena: websites | 796 | 1013 | Codestral 2508 |
| Design Arena: UI components | Not measured | 1017 | Only Codestral 2508 measured |
| Design Arena: game dev | Not measured | 968 | Only Codestral 2508 measured |
| Design Arena: data viz | Not measured | 1017 | Only Codestral 2508 measured |
| Design Arena: 3D | Not measured | 1020 | Only Codestral 2508 measured |
| Design Arena: all code categories | Not measured | 1007 | 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 index20 boards, none shared
| Benchmark | Nova Pro 1.0 | Codestral 2508 | Leader |
|---|---|---|---|
| IFBench | 38.1% | Not measured | Only Nova Pro 1.0 measured |
| Long context reasoning (AA-LCR) | 21.0% | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text | 1259 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: instruction following | 1235 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: creative writing | 1212 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Vision | 980 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: English | 1276 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: non-English | 1233 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: Chinese | 1244 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: German | 1243 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: Japanese | 1200 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: Korean | 1203 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: French | 1271 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: Spanish | 1182 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: Russian | 1240 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: multi-turn | 1246 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: longer queries | 1255 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: writing and language | 1247 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: entertainment and media | 1210 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Vision: English | 987 | Not measured | Only Nova Pro 1.0 measured |
| Neither model has a result on the other 26 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Nova Pro 1.0 | Codestral 2508 | 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
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 | Amazon Nova Pro 1.0 | Mistral Codestral 2508 |
|---|---|---|
| Maker | Amazon | Mistral AI |
| Weights | No public weights listed | No public weights listed |
| Released | December 5, 2024 | August 1, 2025 |
| Context window | 300K | 256K |
| Input $/Mtok | $0.80 | $0.30 |
| Output $/Mtok | $3.20 | $0.90 |
| 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 Nova Pro 1.0 better than Codestral 2508 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Nova Pro 1.0 has the edge where the context window is larger, 300K against 256K tokens, and where the benchmark that matters is Design Arena: websites, where it leads.
Which is cheaper, Nova Pro 1.0 or Codestral 2508?
Nova Pro 1.0 costs $0.80 per million input tokens and $3.20 per million output tokens; Codestral 2508 costs $0.30 and $0.90. Cost per solved task is known for neither of them.
Which has the bigger context window, Nova Pro 1.0 or Codestral 2508?
Nova Pro 1.0, with 300K tokens against 256K.
How many benchmarks is the Nova Pro 1.0 vs Codestral 2508 comparison based on?
1 benchmarks have a result for both models as of October 21, 2026. Nova Pro 1.0's coding index rests on 0 independent benchmarks and Codestral 2508's on 0. Where only one model has a result, the page says so instead of naming a winner.