Model comparison
Kimi K2.5 vs Solar Pro4
Kimi K2.5 is the stronger model overall, scoring 48.1 to 42.1 on the Noometry Index. Solar Pro4 costs 1.7× less per token, which makes it the better buy when Kimi K2.5's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
UpstageSummary
- They share 18 benchmarks with published results for both. Kimi K2.5 scores higher in 8 categories and Solar Pro4 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2.5 leads 53.6 to 39.8.
- Solar Pro4 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.45 / $2.25 for Kimi K2.5.
- Solar Pro4 accepts more context: 524K tokens versus 262K.
- Kimi K2.5 has downloadable open weights; the other is API-only.
Side by side
| Kimi K2.5 | Solar Pro4 | |
|---|---|---|
| Provider | Moonshot AI | Upstage |
| Noometry Index | 48.1 | 42.1 |
| Released | 2026-01-27 | 2026-08-06 |
| Weights | Open | Proprietary |
| Context window | 262K | 524K |
| Max output | 262K | 131K |
| Input $ / M tokens | $0.45 | $0.30 |
| Output $ / M tokens | $2.25 | $1.20 |
| Results tracked | 51 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.5 leads
Kimi K2.5: 48.8 (#53), Solar Pro4: 40.1 (#149)
| Benchmark | Kimi K2.5 | Solar Pro4 |
|---|---|---|
| LMArena WebDev | 1437 | 1371 |
| LMArena Coding | 1474 | 1437 |
| SWE-bench Verified | 73.8% | — |
| SWE-bench Verified (bash only) | 70.8% | — |
| SWE-bench Multilingual | 67.3% | — |
| SciCode | 49% | — |
| WeirdML | 45.6% | — |
| ALE-Bench | 821.65 | — |
Agentic & Tool Use Not comparable
Kimi K2.5: 34.2 (#48), Solar Pro4: —
| Benchmark | Kimi K2.5 | Solar Pro4 |
|---|---|---|
| Terminal-Bench | 43.2% | — |
| OSWorld | 63.3% | — |
| Vending-Bench 2 | 1,198 | — |
Reasoning Kimi K2.5 leads
Kimi K2.5: 31.2 (#80), Solar Pro4: 28.5 (#104)
| Benchmark | Kimi K2.5 | Solar Pro4 |
|---|---|---|
| LMArena Hard Prompts | 1453 | 1399 |
| ARC-AGI-2 | 11.8% | — |
| SimpleBench | 46.8% | — |
| Kagi LLM Benchmark | 78.5% | — |
| NYT Connections (extended) | 69.9% | — |
| ARC-AGI-1 | 65.3% | — |
| CritPt | 3.1% | — |
| Chess Puzzles | 12% | — |
| EnigmaEval | 3.4% | — |
| Thematic Generalization | 69.4% | — |
| Epoch Capabilities Index | 148.03 | — |
Math Kimi K2.5 leads
Kimi K2.5: 51.8 (#53), Solar Pro4: 38.8 (#128)
| Benchmark | Kimi K2.5 | Solar Pro4 |
|---|---|---|
| LMArena Math | 1470 | 1416 |
| MathArena Final-Answer Competitions | 62.3% | — |
| OTIS Mock AIME 2024-2025 | 92.2% | — |
| FrontierMath (Feb 2025 set) | 27.9% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Kimi K2.5 leads
Kimi K2.5: 53.6 (#56), Solar Pro4: 39.8 (#129)
| Benchmark | Kimi K2.5 | Solar Pro4 |
|---|---|---|
| LMArena Expert | 1466 | 1427 |
| GPQA Diamond | 87.6% | — |
| Humanity's Last Exam | 24.4% | — |
| SimpleQA Verified | 34.3% | — |
| Vectara Hallucination Rate | 14.2% | — |
Multimodal Not comparable
Kimi K2.5: 41.1 (#39), Solar Pro4: —
| Benchmark | Kimi K2.5 | Solar Pro4 |
|---|---|---|
| LMArena Vision | 1269 | — |
| LMArena Document | 1430 | — |
Multilingual Kimi K2.5 leads
Kimi K2.5: 53.9 (#53), Solar Pro4: 48.7 (#139)
| Benchmark | Kimi K2.5 | Solar Pro4 |
|---|---|---|
| LMArena Non-English | 1433 | 1361 |
| LMArena Chinese | 1495 | 1415 |
| LMArena French | 1454 | 1397 |
| LMArena German | 1441 | 1364 |
| LMArena Japanese | 1421 | 1309 |
| LMArena Korean | 1410 | 1382 |
| LMArena Russian | 1435 | 1360 |
| LMArena Spanish | 1450 | 1401 |
Instruction Following Kimi K2.5 leads
Kimi K2.5: 75.3 (#64), Solar Pro4: 72.7 (#132)
| Benchmark | Kimi K2.5 | Solar Pro4 |
|---|---|---|
| LMArena Instruction Following | 1431 | 1377 |
Long Context Kimi K2.5 leads
Kimi K2.5: 52.1 (#7), Solar Pro4: 42.1 (#130)
| Benchmark | Kimi K2.5 | Solar Pro4 |
|---|---|---|
| LMArena Longer Query | 1445 | 1381 |
| Fiction.LiveBench | 86.1% | — |
| CL-bench | 19.3% | — |
| CL-bench Life | 13.2% | — |
Writing & Preference Kimi K2.5 leads
Kimi K2.5: 65.1 (#53), Solar Pro4: 56.5 (#138)
| Benchmark | Kimi K2.5 | Solar Pro4 |
|---|---|---|
| LMArena Text | 1445 | 1386 |
| LMArena Creative Writing | 1423 | 1316 |
| LMArena Multi-Turn | 1444 | 1385 |
| EQ-Bench Creative Writing | 1579 | — |
Frequently asked questions
Is Kimi K2.5 better than Solar Pro4?
Kimi K2.5 is the stronger model overall, scoring 48.1 to 42.1 on the Noometry Index. Solar Pro4 costs 1.7× less per token, which makes it the better buy when Kimi K2.5's lead doesn't matter for your workload.
Which is cheaper, Kimi K2.5 or Solar Pro4?
Solar Pro4 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Kimi K2.5 lists at $0.45 and $2.25.
Is Kimi K2.5 or Solar Pro4 better for coding?
Kimi K2.5 scores higher on coding benchmarks: 48.8 versus 40.1 in the Noometry coding category.
Which has the bigger context window?
Solar Pro4 does, with 524K tokens against 262K.
How many benchmarks do Kimi K2.5 and Solar Pro4 share?
18 benchmarks have published results for both models. Kimi K2.5 has 51 scored results on Noometry and Solar Pro4 has 18.