Model comparison
Codestral vs Solar Pro4
Solar Pro4 is the stronger model overall, scoring 42.1 to 30.6 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AI
UpstageSummary
- The widest gap is in coding, where Solar Pro4 leads 40.1 to 27.3.
- Codestral is cheaper at $0.30 / $0.90 per million input/output tokens, against $0.30 / $1.20 for Solar Pro4.
- Solar Pro4 accepts more context: 524K tokens versus 256K.
Side by side
| Codestral | Solar Pro4 | |
|---|---|---|
| Provider | Mistral AI | Upstage |
| Noometry Index | 30.6 | 42.1 |
| Released | 2024-05-29 | 2026-08-06 |
| Weights | Proprietary | Proprietary |
| Context window | 256K | 524K |
| Max output | 8K | 131K |
| Input $ / M tokens | $0.30 | $0.30 |
| Output $ / M tokens | $0.90 | $1.20 |
| Results tracked | 7 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Solar Pro4 leads
Codestral: 27.3 (#321), Solar Pro4: 40.1 (#149)
| Benchmark | Codestral | Solar Pro4 |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| LMArena WebDev | — | 1371 |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1437 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Reasoning Solar Pro4 leads
Codestral: 19.8 (#251), Solar Pro4: 28.5 (#104)
| Benchmark | Codestral | Solar Pro4 |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| LMArena Hard Prompts | — | 1399 |
Math Not comparable
Codestral: —, Solar Pro4: 38.8 (#128)
| Benchmark | Codestral | Solar Pro4 |
|---|---|---|
| LMArena Math | — | 1416 |
Knowledge Not comparable
Codestral: —, Solar Pro4: 39.8 (#129)
| Benchmark | Codestral | Solar Pro4 |
|---|---|---|
| LMArena Expert | — | 1427 |
Multilingual Not comparable
Codestral: —, Solar Pro4: 48.7 (#139)
| Benchmark | Codestral | Solar Pro4 |
|---|---|---|
| LMArena Non-English | — | 1361 |
| LMArena Chinese | — | 1415 |
| LMArena French | — | 1397 |
| LMArena German | — | 1364 |
| LMArena Japanese | — | 1309 |
| LMArena Korean | — | 1382 |
| LMArena Russian | — | 1360 |
| LMArena Spanish | — | 1401 |
Instruction Following Not comparable
Codestral: —, Solar Pro4: 72.7 (#132)
| Benchmark | Codestral | Solar Pro4 |
|---|---|---|
| LMArena Instruction Following | — | 1377 |
Long Context Not comparable
Codestral: —, Solar Pro4: 42.1 (#130)
| Benchmark | Codestral | Solar Pro4 |
|---|---|---|
| LMArena Longer Query | — | 1381 |
Writing & Preference Not comparable
Codestral: —, Solar Pro4: 56.5 (#138)
| Benchmark | Codestral | Solar Pro4 |
|---|---|---|
| LMArena Text | — | 1386 |
| LMArena Creative Writing | — | 1316 |
| LMArena Multi-Turn | — | 1385 |
Frequently asked questions
Is Codestral better than Solar Pro4?
Solar Pro4 is the stronger model overall, scoring 42.1 to 30.6 on the Noometry Index.
Which is cheaper, Codestral or Solar Pro4?
Codestral is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; Solar Pro4 lists at $0.30 and $1.20.
Is Codestral or Solar Pro4 better for coding?
Solar Pro4 scores higher on coding benchmarks: 40.1 versus 27.3 in the Noometry coding category.
Which has the bigger context window?
Solar Pro4 does, with 524K tokens against 256K.
How many benchmarks do Codestral and Solar Pro4 share?
0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Solar Pro4 has 18.