Model comparison
Mistral Medium vs Solar Pro4
Solar Pro4 is the stronger model overall, scoring 42.1 to 36.3 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AI
UpstageSummary
- They share 17 benchmarks with published results for both. Mistral Medium scores higher in 4 categories and Solar Pro4 in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Solar Pro4 leads 39.8 to 25.0.
- Solar Pro4 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- Solar Pro4 accepts more context: 524K tokens versus 262K.
- Mistral Medium has downloadable open weights; the other is API-only.
Side by side
| Mistral Medium | Solar Pro4 | |
|---|---|---|
| Provider | Mistral AI | Upstage |
| Noometry Index | 36.3 | 42.1 |
| Released | 2023-12-11 | 2026-08-06 |
| Weights | Open | Proprietary |
| Context window | 262K | 524K |
| Max output | 262K | 131K |
| Input $ / M tokens | $1.50 | $0.30 |
| Output $ / M tokens | $7.50 | $1.20 |
| Results tracked | 36 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Solar Pro4 leads
Mistral Medium: 34.2 (#243), Solar Pro4: 40.1 (#149)
| Benchmark | Mistral Medium | Solar Pro4 |
|---|---|---|
| LMArena Coding | 1434 | 1437 |
| FrontierCode | 8% | — |
| LMArena WebDev | — | 1371 |
| SciCode | 40.2% | — |
| WeirdML | 43.7% | — |
| ALE-Bench | 763.98 | — |
Agentic & Tool Use Not comparable
Mistral Medium: 28.3 (#90), Solar Pro4: —
| Benchmark | Mistral Medium | Solar Pro4 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.7% | — |
Reasoning Solar Pro4 leads
Mistral Medium: 24.0 (#167), Solar Pro4: 28.5 (#104)
| Benchmark | Mistral Medium | Solar Pro4 |
|---|---|---|
| LMArena Hard Prompts | 1426 | 1399 |
| Kagi LLM Benchmark | 50% | — |
| CritPt | 0% | — |
| DTBench | 75.5% | — |
| LMCA | 26.1% | — |
| Surface Evolver Bench | 26.9% | — |
Math Solar Pro4 leads
Mistral Medium: 28.1 (#245), Solar Pro4: 38.8 (#128)
| Benchmark | Mistral Medium | Solar Pro4 |
|---|---|---|
| LMArena Math | 1408 | 1416 |
| OTIS Mock AIME 2024-2025 | 32.2% | — |
| ProofBench | 9% | — |
| MATH Level 5 | 81.6% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Solar Pro4 leads
Mistral Medium: 25.0 (#265), Solar Pro4: 39.8 (#129)
| Benchmark | Mistral Medium | Solar Pro4 |
|---|---|---|
| LMArena Expert | 1408 | 1427 |
| GPQA Diamond | 59.5% | — |
| Humanity's Last Exam | 4.5% | — |
| Vectara Hallucination Rate | 22.7% | — |
Multimodal Not comparable
Mistral Medium: 35.3 (#88), Solar Pro4: —
| Benchmark | Mistral Medium | Solar Pro4 |
|---|---|---|
| LMArena Vision | 1172 | — |
Multilingual Mistral Medium leads
Mistral Medium: 52.1 (#91), Solar Pro4: 48.7 (#139)
| Benchmark | Mistral Medium | Solar Pro4 |
|---|---|---|
| LMArena Non-English | 1408 | 1361 |
| LMArena Chinese | 1447 | 1415 |
| LMArena French | 1459 | 1397 |
| LMArena German | 1432 | 1364 |
| LMArena Japanese | 1378 | 1309 |
| LMArena Korean | 1380 | 1382 |
| LMArena Russian | 1411 | 1360 |
| LMArena Spanish | 1433 | 1401 |
Instruction Following Mistral Medium leads
Mistral Medium: 73.7 (#116), Solar Pro4: 72.7 (#132)
| Benchmark | Mistral Medium | Solar Pro4 |
|---|---|---|
| LMArena Instruction Following | 1398 | 1377 |
Long Context Too close to call
Mistral Medium: 42.9 (#114), Solar Pro4: 42.1 (#130)
| Benchmark | Mistral Medium | Solar Pro4 |
|---|---|---|
| LMArena Longer Query | 1406 | 1381 |
Writing & Preference Mistral Medium leads
Mistral Medium: 60.0 (#103), Solar Pro4: 56.5 (#138)
| Benchmark | Mistral Medium | Solar Pro4 |
|---|---|---|
| LMArena Text | 1424 | 1386 |
| LMArena Creative Writing | 1391 | 1316 |
| LMArena Multi-Turn | 1418 | 1385 |
| Short-Story Creative Writing | 77.3% | — |
Frequently asked questions
Is Mistral Medium better than Solar Pro4?
Solar Pro4 is the stronger model overall, scoring 42.1 to 36.3 on the Noometry Index.
Which is cheaper, Mistral Medium or Solar Pro4?
Solar Pro4 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is Mistral Medium or Solar Pro4 better for coding?
Solar Pro4 scores higher on coding benchmarks: 40.1 versus 34.2 in the Noometry coding category.
Which has the bigger context window?
Solar Pro4 does, with 524K tokens against 262K.
How many benchmarks do Mistral Medium and Solar Pro4 share?
17 benchmarks have published results for both models. Mistral Medium has 36 scored results on Noometry and Solar Pro4 has 18.