Mistral Large 2407 vs Solar Pro 3
Solar Pro 3 leads Mistral Large 2407 on the Artificial Analysis Intelligence Index, 7.8 to 7.6, and Solar Pro 3 costs 10.0x less per output token ($0.60 vs $6.00 per million). Updated October 22, 2026; 6 benchmarks have a result for both.
Mistral Large 2407 or Solar Pro 3: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Mistral Large 2407 for work measured by AA Intelligence Index or τ²-Bench Telecom, where it leads.
- Shared results
- 6
- Mistral Large 2407 only
- 11
- Solar Pro 3 only
- 4
- Like-for-like categories
- 4 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
Solar Pro 3
Solar Pro 3 leads, 7.8 against 7.6.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Solar Pro 3 has a AA Agentic Index result, 1.4.
Directional only
Long documents
Listed context window
No call
Both take 131K tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Solar Pro 3
Mistral Large 2407 $0.0050, Solar Pro 3 $0.0004 per turn.
List prices
At a glance
- Coding index
- Mistral Large 2407 not benchmarked, Solar Pro 3 not benchmarked.
- Widest category
- Agentic work, 53.2 points apart on average over 1 shared benchmark.
- Widest single gap
- τ²-Bench Telecom: Mistral Large 2407 33.0% against Solar Pro 3 86.3%, 53.2 points apart on a 0 to 100 scale.
- Output price
- Mistral Large 2407 $6.00 against Solar Pro 3 $0.60 per million output tokens, 10.0x apart.
- Context window
- Both take 131K tokens.
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 | Mistral Large 2407 | Bars | Solar Pro 3 | Ties |
|---|---|---|---|---|
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 0 | 2 | ||
| General | 0 | 2 | ||
| All shared boards | 0 | 6 |
CodingDirectional onlySix of these boards feed the Vibe Coding Index4 boards, none shared
| Benchmark | Mistral Large 2407 | Solar Pro 3 | Leader |
|---|---|---|---|
| AA Coding Index | Not measured | 16.2 | Only Solar Pro 3 measured |
| LiveCodeBench (Artificial Analysis run) | 26.7% | Not measured | Only Mistral Large 2407 measured |
| SciCode | Not measured | 25.5% | Only Solar Pro 3 measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 7.6% | Only Solar Pro 3 measured |
| Neither model has a result on the other 35 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Mistral Large 2407 | Solar Pro 3 | Leader |
|---|---|---|---|
| AA Intelligence Index | 7.6 | 7.8 | Solar Pro 3 |
| 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 | Mistral Large 2407 | Solar Pro 3 | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 1.4 | Only Solar Pro 3 measured |
| τ²-Bench Telecom | 33.0% | 86.3% | Solar Pro 3 |
| Neither model has a result on the other 39 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Mistral Large 2407 | Solar Pro 3 | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 47.2% | 72.4% | Solar Pro 3 |
| Humanity's Last Exam (Artificial Analysis run) | 2.9% | 10.3% | Solar Pro 3 |
| GPQA Diamond (Epoch AI run) | 49.0% | Not measured | Only Mistral Large 2407 measured |
| SimpleBench | 22.5% | Not measured | Only Mistral Large 2407 measured |
| Neither model has a result on the other 18 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
| Benchmark | Mistral Large 2407 | Solar Pro 3 | Leader |
|---|---|---|---|
| AA Math Index | 0.0 | Not measured | Only Mistral Large 2407 measured |
| AIME 2025 (Artificial Analysis run) | 0.0% | Not measured | Only Mistral Large 2407 measured |
| OTIS Mock AIME | 8.5% | Not measured | Only Mistral Large 2407 measured |
| MATH level 5 | 44.8% | Not measured | Only Mistral Large 2407 measured |
| Neither model has a result on the other 9 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Mistral Large 2407 | Solar Pro 3 | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 68.3% | Not measured | Only Mistral Large 2407 measured |
| MMLU | 80.0% | Not measured | Only Mistral Large 2407 measured |
| Neither model has a result on the other 16 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Mistral Large 2407 | Solar Pro 3 | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Mistral Large 2407 | Solar Pro 3 | Leader |
|---|---|---|---|
| IFBench | 31.6% | 71.2% | Solar Pro 3 |
| Long context reasoning (AA-LCR) | 2.0% | 32.3% | Solar Pro 3 |
| DTBench | 61.2% | Not measured | Only Mistral Large 2407 measured |
| Creative writing (Lech Mazur) | 69.0% | Not measured | Only Mistral Large 2407 measured |
| Neither model has a result on the other 42 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Mistral Large 2407 | Solar Pro 3 | 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
Solar Pro 3 costs less
Repository review
50K input + 3K output tokens
Solar Pro 3 costs less
Agent loop
200K input + 10K output tokens
Solar Pro 3 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 Large 2407 | Upstage Solar Pro 3 |
|---|---|---|
| Maker | Mistral AI | Upstage |
| Weights | No public weights listed | No public weights listed |
| Released | November 19, 2024 | January 27, 2026 |
| Context window | 131K | 131K |
| Input $/Mtok | $2.00 | $0.15 |
| Output $/Mtok | $6.00 | $0.60 |
| 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 Mistral Large 2407 better than Solar Pro 3 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Mistral Large 2407 for work measured by AA Intelligence Index or τ²-Bench Telecom, where it leads.
Which is cheaper, Mistral Large 2407 or Solar Pro 3?
Mistral Large 2407 costs $2.00 per million input tokens and $6.00 per million output tokens; Solar Pro 3 costs $0.15 and $0.60. Cost per solved task is known for neither of them.
Which has the bigger context window, Mistral Large 2407 or Solar Pro 3?
Neither: both take 131K tokens.
How many benchmarks is the Mistral Large 2407 vs Solar Pro 3 comparison based on?
6 benchmarks have a result for both models as of October 22, 2026. Mistral Large 2407's coding index rests on 0 independent benchmarks and Solar Pro 3's on 0. Where only one model has a result, the page says so instead of naming a winner.