Model comparison
Mistral Large vs Solar Pro4
Solar Pro4 is the stronger model overall, scoring 42.1 to 31.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AI
UpstageSummary
- They share 17 benchmarks with published results for both. Mistral Large scores higher in 0 categories and Solar Pro4 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Solar Pro4 leads 38.8 to 18.2.
- Solar Pro4 is cheaper at $0.30 / $1.20 per million input/output tokens, against $2 / $6 for Mistral Large.
- Solar Pro4 accepts more context: 524K tokens versus 131K.
- Mistral Large has downloadable open weights; the other is API-only.
Side by side
| Mistral Large | Solar Pro4 | |
|---|---|---|
| Provider | Mistral AI | Upstage |
| Noometry Index | 31.9 | 42.1 |
| Released | 2024-02-26 | 2026-08-06 |
| Weights | Open | Proprietary |
| Context window | 131K | 524K |
| Max output | 16K | 131K |
| Input $ / M tokens | $2 | $0.30 |
| Output $ / M tokens | $6 | $1.20 |
| Results tracked | 51 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Solar Pro4 leads
Mistral Large: 34.3 (#240), Solar Pro4: 40.1 (#149)
| Benchmark | Mistral Large | Solar Pro4 |
|---|---|---|
| LMArena Coding | 1277 | 1437 |
| LMArena WebDev | — | 1371 |
| SciCode | 36.2% | — |
| BigCodeBench Instruct | 30% | — |
| LiveBench Coding | 47.1% | — |
| BigCodeBench Complete | 38.3% | — |
| ALE-Bench | 264.7 | — |
| HumanEval+ | 62.2% | — |
| MBPP+ | 59.5% | — |
Agentic & Tool Use Not comparable
Mistral Large: 28.6 (#89), Solar Pro4: —
| Benchmark | Mistral Large | Solar Pro4 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 38.4% | — |
Reasoning Solar Pro4 leads
Mistral Large: 15.8 (#310), Solar Pro4: 28.5 (#104)
| Benchmark | Mistral Large | Solar Pro4 |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1399 |
| SimpleBench | 22.5% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | 43.5% | — |
| DTBench | 65.1% | — |
| LiveBench Data Analysis | 50.1% | — |
| LMCA | 16.7% | — |
| Epoch Capabilities Index | 128.52 | — |
| ForecastBench | 57.1 | — |
| LiveBench | 48.4% | — |
Math Solar Pro4 leads
Mistral Large: 18.2 (#291), Solar Pro4: 38.8 (#128)
| Benchmark | Mistral Large | Solar Pro4 |
|---|---|---|
| LMArena Math | 1262 | 1416 |
| OTIS Mock AIME 2024-2025 | 8.5% | — |
| Omni-MATH | 28.1% | — |
| LiveBench Math | 42.5% | — |
| MATH Level 5 | 50.3% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Solar Pro4 leads
Mistral Large: 30.1 (#230), Solar Pro4: 39.8 (#129)
| Benchmark | Mistral Large | Solar Pro4 |
|---|---|---|
| LMArena Expert | 1232 | 1427 |
| GPQA Diamond | 51.3% | — |
| MMLU-Pro | 59.9% | — |
| Confabulations | 21.4% | — |
| Vectara Hallucination Rate | 4.5% | — |
| GPQA (HELM) | 43.5% | — |
| MMLU | 80% | — |
Multilingual Solar Pro4 leads
Mistral Large: 40.0 (#219), Solar Pro4: 48.7 (#139)
| Benchmark | Mistral Large | Solar Pro4 |
|---|---|---|
| LMArena Non-English | 1237 | 1361 |
| LMArena Chinese | 1240 | 1415 |
| LMArena French | 1325 | 1397 |
| LMArena German | 1254 | 1364 |
| LMArena Japanese | 1188 | 1309 |
| LMArena Korean | 1202 | 1382 |
| LMArena Russian | 1257 | 1360 |
| LMArena Spanish | 1268 | 1401 |
Instruction Following Solar Pro4 leads
Mistral Large: 67.9 (#191), Solar Pro4: 72.7 (#132)
| Benchmark | Mistral Large | Solar Pro4 |
|---|---|---|
| LMArena Instruction Following | 1249 | 1377 |
| LiveBench Instruction Following | 67.9% | — |
| IFEval | 87.7% | — |
Long Context Solar Pro4 leads
Mistral Large: 38.3 (#199), Solar Pro4: 42.1 (#130)
| Benchmark | Mistral Large | Solar Pro4 |
|---|---|---|
| LMArena Longer Query | 1261 | 1381 |
Writing & Preference Solar Pro4 leads
Mistral Large: 40.7 (#242), Solar Pro4: 56.5 (#138)
| Benchmark | Mistral Large | Solar Pro4 |
|---|---|---|
| LMArena Text | 1266 | 1386 |
| LMArena Creative Writing | 1243 | 1316 |
| LMArena Multi-Turn | 1260 | 1385 |
| Short-Story Creative Writing | 69% | — |
| EQ-Bench Creative Writing | 985 | — |
| WildBench | 80.1% | — |
| LiveBench Language | 39.4% | — |
Frequently asked questions
Is Mistral Large better than Solar Pro4?
Solar Pro4 is the stronger model overall, scoring 42.1 to 31.9 on the Noometry Index.
Which is cheaper, Mistral Large or Solar Pro4?
Solar Pro4 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Mistral Large lists at $2 and $6.
Is Mistral Large or Solar Pro4 better for coding?
Solar Pro4 scores higher on coding benchmarks: 40.1 versus 34.3 in the Noometry coding category.
Which has the bigger context window?
Solar Pro4 does, with 524K tokens against 131K.
How many benchmarks do Mistral Large and Solar Pro4 share?
17 benchmarks have published results for both models. Mistral Large has 51 scored results on Noometry and Solar Pro4 has 18.