Model comparison
Kimi K2.6 vs Step 3.5 Flash
Kimi K2.6 is the stronger model overall, scoring 47.7 to 42.3 on the Noometry Index. Step 3.5 Flash costs 11× less per token, which makes it the better buy when Kimi K2.6's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
StepFunSummary
- They share 19 benchmarks with published results for both. Kimi K2.6 scores higher in 8 categories and Step 3.5 Flash in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K2.6 leads 40.5 to 22.2.
- The biggest single-benchmark swing is NYT Connections (extended): 87.2% for Kimi K2.6 and 28.4% for Step 3.5 Flash.
- Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.95 / $4 for Kimi K2.6.
- Kimi K2.6 accepts more context: 262K tokens versus 256K.
Side by side
| Kimi K2.6 | Step 3.5 Flash | |
|---|---|---|
| Provider | Moonshot AI | StepFun |
| Noometry Index | 47.7 | 42.3 |
| Released | 2026-04-20 | 2026-01-29 |
| Weights | Open | Open |
| Context window | 262K | 256K |
| Max output | 262K | 256K |
| Input $ / M tokens | $0.95 | $0.10 |
| Output $ / M tokens | $4 | $0.30 |
| Results tracked | 51 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.6 leads
Kimi K2.6: 50.7 (#43), Step 3.5 Flash: 42.4 (#105)
| Benchmark | Kimi K2.6 | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1488 | 1436 |
| SWE-bench Verified | 76.7% | — |
| LMArena WebDev | 1509 | — |
| SciCode | 53.5% | — |
| WeirdML | 55.9% | — |
| ALE-Bench | 1,093 | — |
Agentic & Tool Use Not comparable
Kimi K2.6: 21.9 (#137), Step 3.5 Flash: —
| Benchmark | Kimi K2.6 | Step 3.5 Flash |
|---|---|---|
| OSWorld 2.0 | 4.6% | — |
| ExploitBench | 18.4% | — |
| GBAEval | 0.9% | — |
| GDP.pdf | 12% | — |
| Vending-Bench 2 | 6,205 | — |
Reasoning Kimi K2.6 leads
Kimi K2.6: 40.5 (#55), Step 3.5 Flash: 22.2 (#202)
| Benchmark | Kimi K2.6 | Step 3.5 Flash |
|---|---|---|
| NYT Connections (extended) | 87.2% | 28.4% |
| LMArena Hard Prompts | 1470 | 1411 |
| CritPt | 8% | — |
| Chess Puzzles | 26% | — |
| EBR-Bench | 2.4% | — |
| Mystery Game Puzzles | 18% | — |
| DTBench | 90.9% | — |
| LMCA | 37.3% | — |
| Epoch Capabilities Index | 151.05 | — |
Math Kimi K2.6 leads
Kimi K2.6: 57.0 (#41), Step 3.5 Flash: 42.6 (#84)
| Benchmark | Kimi K2.6 | Step 3.5 Flash |
|---|---|---|
| MathArena Final-Answer Competitions | 72.9% | 66.8% |
| LMArena Math | 1475 | 1408 |
| FrontierMath (Tiers 1-3) | 57.2% | — |
| FrontierMath Tier 4 | 25.6% | — |
| OTIS Mock AIME 2024-2025 | 96.1% | — |
| ProofBench | 16% | — |
| FrontierMath (Feb 2025 set) | 39% | — |
| FrontierMath Tier 4 (v1) | 14.6% | — |
Knowledge Kimi K2.6 leads
Kimi K2.6: 54.0 (#54), Step 3.5 Flash: 39.6 (#132)
| Benchmark | Kimi K2.6 | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1491 | 1421 |
| GPQA Diamond | 90.8% | — |
| SimpleQA Verified | 34.9% | — |
| Vectara Hallucination Rate | 10.8% | — |
Multimodal Not comparable
Kimi K2.6: 31.6 (#103), Step 3.5 Flash: —
| Benchmark | Kimi K2.6 | Step 3.5 Flash |
|---|---|---|
| LMArena Vision | 1283 | — |
| Blueprint-Bench 2 | 3.9% | — |
| Furniture Assembly | 21.7% | — |
| LMArena Document | 1451 | — |
Multilingual Kimi K2.6 leads
Kimi K2.6: 54.9 (#37), Step 3.5 Flash: 50.5 (#119)
| Benchmark | Kimi K2.6 | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1446 | 1385 |
| LMArena Chinese | 1521 | 1447 |
| LMArena French | 1471 | 1421 |
| LMArena German | 1450 | 1405 |
| LMArena Japanese | 1443 | 1354 |
| LMArena Korean | 1427 | 1352 |
| LMArena Russian | 1446 | 1385 |
| LMArena Spanish | 1464 | 1419 |
Instruction Following Kimi K2.6 leads
Kimi K2.6: 76.3 (#43), Step 3.5 Flash: 73.1 (#124)
| Benchmark | Kimi K2.6 | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1451 | 1385 |
Long Context Kimi K2.6 leads
Kimi K2.6: 44.9 (#52), Step 3.5 Flash: 42.8 (#117)
| Benchmark | Kimi K2.6 | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1468 | 1402 |
Writing & Preference Kimi K2.6 leads
Kimi K2.6: 68.5 (#26), Step 3.5 Flash: 58.8 (#113)
| Benchmark | Kimi K2.6 | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1455 | 1403 |
| LMArena Creative Writing | 1434 | 1357 |
| LMArena Multi-Turn | 1453 | 1405 |
| EQ-Bench Creative Writing | 1725 | — |
| EQ-Bench 4 | 1202 | — |
Frequently asked questions
Is Kimi K2.6 better than Step 3.5 Flash?
Kimi K2.6 is the stronger model overall, scoring 47.7 to 42.3 on the Noometry Index. Step 3.5 Flash costs 11× less per token, which makes it the better buy when Kimi K2.6's lead doesn't matter for your workload.
Which is cheaper, Kimi K2.6 or Step 3.5 Flash?
Step 3.5 Flash is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Kimi K2.6 lists at $0.95 and $4.
Is Kimi K2.6 or Step 3.5 Flash better for coding?
Kimi K2.6 scores higher on coding benchmarks: 50.7 versus 42.4 in the Noometry coding category.
Which has the bigger context window?
Kimi K2.6 does, with 262K tokens against 256K.
How many benchmarks do Kimi K2.6 and Step 3.5 Flash share?
19 benchmarks have published results for both models. Kimi K2.6 has 51 scored results on Noometry and Step 3.5 Flash has 19.