Granite 4.0 Micro vs Mistral Large 2407
Mistral Large 2407 leads Granite 4.0 Micro on the Artificial Analysis Intelligence Index, 7.6 to 5.1, and Granite 4.0 Micro costs 53.6x less per output token ($0.112 vs $6.00 per million). Updated October 22, 2026; 12 benchmarks have a result for both.
Granite 4.0 Micro or Mistral Large 2407: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Granite 4.0 Micro for output tokens 53.6x cheaper ($0.112 vs $6.00 per million) and work measured by LiveCodeBench (Artificial Analysis run) or AA Intelligence Index, where it leads.
- Shared results
- 12
- Granite 4.0 Micro only
- 1
- Mistral Large 2407 only
- 5
- Like-for-like categories
- 7 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
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
Mistral Large 2407
Mistral Large 2407 leads, 7.6 against 5.1.
Same board, both measured
Long documents
Listed context window
Mistral Large 2407
Mistral Large 2407 takes 131K tokens against 131K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Granite 4.0 Micro
Granite 4.0 Micro $0.0001, Mistral Large 2407 $0.0050 per turn.
List prices
At a glance
- Coding index
- Granite 4.0 Micro not benchmarked, Mistral Large 2407 not benchmarked.
- Widest category
- Knowledge, 23.6 points apart on average over 1 shared benchmark.
- Widest single gap
- MMLU Pro (Artificial Analysis run): Granite 4.0 Micro 44.7% against Mistral Large 2407 68.3%, 23.6 points apart on a 0 to 100 scale.
- Output price
- Granite 4.0 Micro $0.112 against Mistral Large 2407 $6.00 per million output tokens, 53.6x apart.
- Context window
- Granite 4.0 Micro takes 131K tokens, Mistral Large 2407 131K.
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 | Granite 4.0 Micro | Bars | Mistral Large 2407 | Ties |
|---|---|---|---|---|
| Coding | 0 | 1 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 1 | 2 | ||
| Math | 2 | 1 | ||
| Knowledge | 0 | 1 | ||
| General | 1 | 1 | ||
| All shared boards | 4 | 8 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index01
| Benchmark | Granite 4.0 Micro | Mistral Large 2407 | Leader |
|---|---|---|---|
| LiveCodeBench (Artificial Analysis run) | 18.0% | 26.7% | Mistral Large 2407 |
| Terminal-Bench Hard (Artificial Analysis run) | 1.5% | Not measured | Only Granite 4.0 Micro measured |
| Neither model has a result on the other 41 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Granite 4.0 Micro | Mistral Large 2407 | Leader |
|---|---|---|---|
| AA Intelligence Index | 5.1 | 7.6 | Mistral Large 2407 |
| Neither model has a result on the other 1 board here | |||
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Granite 4.0 Micro | Mistral Large 2407 | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 12.6% | 33.0% | Mistral Large 2407 |
| Neither model has a result on the other 41 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index12
| Benchmark | Granite 4.0 Micro | Mistral Large 2407 | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 33.6% | 47.2% | Mistral Large 2407 |
| Humanity's Last Exam (Artificial Analysis run) | 5.0% | 2.9% | Granite 4.0 Micro |
| GPQA Diamond (Epoch AI run) | 28.3% | 49.0% | Mistral Large 2407 |
| SimpleBench | Not measured | 22.5% | Only Mistral Large 2407 measured |
| Neither model has a result on the other 19 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index21
| Benchmark | Granite 4.0 Micro | Mistral Large 2407 | Leader |
|---|---|---|---|
| AA Math Index | 6.0 | 0.0 | Granite 4.0 Micro |
| AIME 2025 (Artificial Analysis run) | 6.0% | 0.0% | Granite 4.0 Micro |
| OTIS Mock AIME | 2.8% | 8.5% | Mistral Large 2407 |
| MATH level 5 | Not measured | 44.8% | Only Mistral Large 2407 measured |
| Neither model has a result on the other 10 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Granite 4.0 Micro | Mistral Large 2407 | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 44.7% | 68.3% | Mistral Large 2407 |
| MMLU | Not measured | 80.0% | Only Mistral Large 2407 measured |
| Neither model has a result on the other 18 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Granite 4.0 Micro | Mistral Large 2407 | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | Granite 4.0 Micro | Mistral Large 2407 | Leader |
|---|---|---|---|
| IFBench | 24.8% | 31.6% | Mistral Large 2407 |
| Long context reasoning (AA-LCR) | 7.0% | 2.0% | Granite 4.0 Micro |
| DTBench | Not measured | 61.2% | Only Mistral Large 2407 measured |
| Creative writing (Lech Mazur) | Not measured | 69.0% | Only Mistral Large 2407 measured |
| Neither model has a result on the other 44 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Granite 4.0 Micro | Mistral Large 2407 | 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
Granite 4.0 Micro costs less
Repository review
50K input + 3K output tokens
Granite 4.0 Micro costs less
Agent loop
200K input + 10K output tokens
Granite 4.0 Micro 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 | IBM Granite 4.0 Micro | Mistral Large 2407 |
|---|---|---|
| Maker | IBM Granite | Mistral AI |
| Weights | Open weights | No public weights listed |
| Released | October 20, 2025 | November 19, 2024 |
| Context window | 131K | 131K |
| Input $/Mtok | $0.017 | $2.00 |
| Output $/Mtok | $0.112 | $6.00 |
| 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 Granite 4.0 Micro better than Mistral Large 2407 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Granite 4.0 Micro for output tokens 53.6x cheaper ($0.112 vs $6.00 per million) and work measured by LiveCodeBench (Artificial Analysis run) or AA Intelligence Index, where it leads.
Which is cheaper, Granite 4.0 Micro or Mistral Large 2407?
Granite 4.0 Micro costs $0.017 per million input tokens and $0.112 per million output tokens; Mistral Large 2407 costs $2.00 and $6.00. Cost per solved task is known for neither of them.
Which has the bigger context window, Granite 4.0 Micro or Mistral Large 2407?
Mistral Large 2407, with 131K tokens against 131K.
How many benchmarks is the Granite 4.0 Micro vs Mistral Large 2407 comparison based on?
12 benchmarks have a result for both models as of October 22, 2026. Granite 4.0 Micro's coding index rests on 0 independent benchmarks and Mistral Large 2407's on 0. Where only one model has a result, the page says so instead of naming a winner.