Model comparison
Kimi K2.6 vs Phi 3 Mini 4k Instruct
Kimi K2.6 is the stronger model overall, scoring 47.7 to 27.9 on the Noometry Index.
Last verified . 18 shared benchmarks.
MicrosoftSummary
- They share 18 benchmarks with published results for both. Kimi K2.6 scores higher in 8 categories and Phi 3 Mini 4k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Kimi K2.6 leads 68.5 to 27.6.
- The biggest single-benchmark swing is Chess Puzzles: 26% for Kimi K2.6 and 0% for Phi 3 Mini 4k Instruct.
Side by side
| Kimi K2.6 | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | Moonshot AI | Microsoft |
| Noometry Index | 47.7 | 27.9 |
| Released | 2026-04-20 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 262K | — |
| Input $ / M tokens | $0.95 | — |
| Output $ / M tokens | $4 | — |
| Results tracked | 51 | 35 |
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), Phi 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | Kimi K2.6 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1488 | 1093 |
| SWE-bench Verified | 76.7% | — |
| LMArena WebDev | 1509 | — |
| SciCode | 53.5% | — |
| WeirdML | 55.9% | — |
| LiveBench Coding | — | 15.5% |
| ALE-Bench | 1,093 | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Agentic & Tool Use Not comparable
Kimi K2.6: 21.9 (#137), Phi 3 Mini 4k Instruct: —
| Benchmark | Kimi K2.6 | Phi 3 Mini 4k Instruct |
|---|---|---|
| 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), Phi 3 Mini 4k Instruct: 14.1 (#328)
| Benchmark | Kimi K2.6 | Phi 3 Mini 4k Instruct |
|---|---|---|
| Chess Puzzles | 26% | 0% |
| LMArena Hard Prompts | 1470 | 1072 |
| NYT Connections (extended) | 87.2% | — |
| CritPt | 8% | — |
| EBR-Bench | 2.4% | — |
| LiveBench Reasoning | — | 26.8% |
| Mystery Game Puzzles | 18% | — |
| DTBench | 90.9% | — |
| LiveBench Data Analysis | — | 34.7% |
| LMCA | 37.3% | — |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | 151.05 | — |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |
Math Kimi K2.6 leads
Kimi K2.6: 57.0 (#41), Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | Kimi K2.6 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1475 | 1111 |
| FrontierMath (Tiers 1-3) | 57.2% | — |
| FrontierMath Tier 4 | 25.6% | — |
| MathArena Final-Answer Competitions | 72.9% | — |
| OTIS Mock AIME 2024-2025 | 96.1% | — |
| ProofBench | 16% | — |
| LiveBench Math | — | 15.7% |
| FrontierMath (Feb 2025 set) | 39% | — |
| FrontierMath Tier 4 (v1) | 14.6% | — |
Knowledge Kimi K2.6 leads
Kimi K2.6: 54.0 (#54), Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | Kimi K2.6 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1491 | 1045 |
| GPQA Diamond | 90.8% | — |
| SimpleQA Verified | 34.9% | — |
| Vectara Hallucination Rate | 10.8% | — |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multimodal Not comparable
Kimi K2.6: 31.6 (#103), Phi 3 Mini 4k Instruct: —
| Benchmark | Kimi K2.6 | Phi 3 Mini 4k Instruct |
|---|---|---|
| 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), Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | Kimi K2.6 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1446 | 1021 |
| LMArena Chinese | 1521 | 1021 |
| LMArena French | 1471 | 1076 |
| LMArena German | 1450 | 1044 |
| LMArena Japanese | 1443 | 935 |
| LMArena Korean | 1427 | 905 |
| LMArena Russian | 1446 | 1022 |
| LMArena Spanish | 1464 | 1085 |
Instruction Following Kimi K2.6 leads
Kimi K2.6: 76.3 (#43), Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | Kimi K2.6 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1451 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
Long Context Kimi K2.6 leads
Kimi K2.6: 44.9 (#52), Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | Kimi K2.6 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1468 | 1044 |
Writing & Preference Kimi K2.6 leads
Kimi K2.6: 68.5 (#26), Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | Kimi K2.6 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1455 | 1073 |
| LMArena Creative Writing | 1434 | 1037 |
| LMArena Multi-Turn | 1453 | 1018 |
| EQ-Bench Creative Writing | 1725 | — |
| EQ-Bench 4 | 1202 | — |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is Kimi K2.6 better than Phi 3 Mini 4k Instruct?
Kimi K2.6 is the stronger model overall, scoring 47.7 to 27.9 on the Noometry Index.
Is Kimi K2.6 or Phi 3 Mini 4k Instruct better for coding?
Kimi K2.6 scores higher on coding benchmarks: 50.7 versus 26.6 in the Noometry coding category.
How many benchmarks do Kimi K2.6 and Phi 3 Mini 4k Instruct share?
18 benchmarks have published results for both models. Kimi K2.6 has 51 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.