Model comparison
Kimi K3 vs Solar Pro4
Kimi K3 is the stronger model overall, scoring 59.5 to 42.1 on the Noometry Index. Solar Pro4 costs 11× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
UpstageSummary
- They share 18 benchmarks with published results for both. Kimi K3 scores higher in 8 categories and Solar Pro4 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K3 leads 74.2 to 38.8.
- Solar Pro4 is cheaper at $0.30 / $1.20 per million input/output tokens, against $3 / $15 for Kimi K3.
- Kimi K3 accepts more context: 1.05M tokens versus 524K.
- Kimi K3 has downloadable open weights; the other is API-only.
Side by side
| Kimi K3 | Solar Pro4 | |
|---|---|---|
| Provider | Moonshot AI | Upstage |
| Noometry Index | 59.5 | 42.1 |
| Released | 2026-07-16 | 2026-08-06 |
| Weights | Open | Proprietary |
| Context window | 1.05M | 524K |
| Max output | 1.05M | 131K |
| Input $ / M tokens | $3 | $0.30 |
| Output $ / M tokens | $15 | $1.20 |
| Results tracked | 53 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K3 leads
Kimi K3: 61.0 (#10), Solar Pro4: 40.1 (#149)
| Benchmark | Kimi K3 | Solar Pro4 |
|---|---|---|
| LMArena WebDev | 1654 | 1371 |
| LMArena Coding | 1508 | 1437 |
| DeepSWE | 68.5% | — |
| FrontierCode | 44.2% | — |
| FrontierSWE | 25.9% | — |
| SciCode | 59.5% | — |
| WeirdML | 82.6% | — |
| ALE-Bench | 1,524 | — |
Agentic & Tool Use Not comparable
Kimi K3: 41.8 (#20), Solar Pro4: —
| Benchmark | Kimi K3 | Solar Pro4 |
|---|---|---|
| APEX-Agents | 50.6% | — |
| τ²-bench Banking | 37.1% | — |
| PostTrainBench | 32% | — |
| GBAEval | 48.3% | — |
| GDP.pdf | 19% | — |
| Vending-Bench 2 | 5,165 | — |
Reasoning Kimi K3 leads
Kimi K3: 63.0 (#17), Solar Pro4: 28.5 (#104)
| Benchmark | Kimi K3 | Solar Pro4 |
|---|---|---|
| LMArena Hard Prompts | 1496 | 1399 |
| ARC-AGI-2 | 60.4% | — |
| SimpleBench | 60.7% | — |
| NYT Connections (extended) | 93.6% | — |
| ARC-AGI-1 | 94.5% | — |
| CritPt | 23.4% | — |
| Chess Puzzles | 39% | — |
| Mystery Game Puzzles | 26% | — |
| DTBench | 91.2% | — |
| LMCA | 52.7% | — |
| Surface Evolver Bench | 95% | — |
| Epoch Capabilities Index | 157.45 | — |
| ForecastBench | 61.1 | — |
Math Kimi K3 leads
Kimi K3: 74.2 (#16), Solar Pro4: 38.8 (#128)
| Benchmark | Kimi K3 | Solar Pro4 |
|---|---|---|
| LMArena Math | 1491 | 1416 |
| FrontierMath (Tiers 1-3) | 72.2% | — |
| FrontierMath Tier 4 | 39% | — |
| MathArena Final-Answer Competitions | 87.8% | — |
| OTIS Mock AIME 2024-2025 | 97.2% | — |
| ProofBench | 87% | — |
Knowledge Kimi K3 leads
Kimi K3: 63.2 (#21), Solar Pro4: 39.8 (#129)
| Benchmark | Kimi K3 | Solar Pro4 |
|---|---|---|
| LMArena Expert | 1521 | 1427 |
| GPQA Diamond | 93.1% | — |
| SimpleQA Verified | 50.6% | — |
Multimodal Not comparable
Kimi K3: 37.8 (#70), Solar Pro4: —
| Benchmark | Kimi K3 | Solar Pro4 |
|---|---|---|
| Blueprint-Bench 2 | 29.5% | — |
| Furniture Assembly | 34.2% | — |
Multilingual Kimi K3 leads
Kimi K3: 56.3 (#21), Solar Pro4: 48.7 (#139)
| Benchmark | Kimi K3 | Solar Pro4 |
|---|---|---|
| LMArena Non-English | 1466 | 1361 |
| LMArena Chinese | 1529 | 1415 |
| LMArena French | 1491 | 1397 |
| LMArena German | 1488 | 1364 |
| LMArena Japanese | 1487 | 1309 |
| LMArena Korean | 1458 | 1382 |
| LMArena Russian | 1482 | 1360 |
| LMArena Spanish | 1472 | 1401 |
Instruction Following Kimi K3 leads
Kimi K3: 77.7 (#14), Solar Pro4: 72.7 (#132)
| Benchmark | Kimi K3 | Solar Pro4 |
|---|---|---|
| LMArena Instruction Following | 1483 | 1377 |
Long Context Kimi K3 leads
Kimi K3: 45.8 (#29), Solar Pro4: 42.1 (#130)
| Benchmark | Kimi K3 | Solar Pro4 |
|---|---|---|
| LMArena Longer Query | 1494 | 1381 |
Writing & Preference Kimi K3 leads
Kimi K3: 76.6 (#4), Solar Pro4: 56.5 (#138)
| Benchmark | Kimi K3 | Solar Pro4 |
|---|---|---|
| LMArena Text | 1476 | 1386 |
| LMArena Creative Writing | 1454 | 1316 |
| LMArena Multi-Turn | 1488 | 1385 |
| EQ-Bench Creative Writing | 2082 | — |
| EQ-Bench 4 | 1339 | — |
Frequently asked questions
Is Kimi K3 better than Solar Pro4?
Kimi K3 is the stronger model overall, scoring 59.5 to 42.1 on the Noometry Index. Solar Pro4 costs 11× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Which is cheaper, Kimi K3 or Solar Pro4?
Solar Pro4 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Kimi K3 lists at $3 and $15.
Is Kimi K3 or Solar Pro4 better for coding?
Kimi K3 scores higher on coding benchmarks: 61.0 versus 40.1 in the Noometry coding category.
Which has the bigger context window?
Kimi K3 does, with 1.05M tokens against 524K.
How many benchmarks do Kimi K3 and Solar Pro4 share?
18 benchmarks have published results for both models. Kimi K3 has 53 scored results on Noometry and Solar Pro4 has 18.