Model comparison
Kimi K2.5 vs Yi-1.5-34B
Kimi K2.5 is the stronger model overall, scoring 47.8 to 30.2 on the Noometry Index.
Last verified . 18 shared benchmarks.
Summary
- They share 18 benchmarks with published results for both. Kimi K2.5 scores higher in 8 categories and Yi-1.5-34B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2.5 leads 53.6 to 14.8.
- The biggest single-benchmark swing is GPQA Diamond: 87.6% for Kimi K2.5 and 32% for Yi-1.5-34B.
Side by side
| Kimi K2.5 | Yi-1.5-34B | |
|---|---|---|
| Provider | Moonshot AI | 01.AI |
| Noometry Index | 47.8 | 30.2 |
| Released | 2026-01-27 | 2024-05-13 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 262K | — |
| Input $ / M tokens | $0.45 | — |
| Output $ / M tokens | $2.25 | — |
| Results tracked | 51 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.5 leads
Kimi K2.5: 48.7 (#48), Yi-1.5-34B: 31.9 (#267)
| Benchmark | Kimi K2.5 | Yi-1.5-34B |
|---|---|---|
| LMArena Coding | 1474 | 1169 |
| SWE-bench Verified | 73.8% | — |
| SWE-bench Verified (bash only) | 70.8% | — |
| LMArena WebDev | 1436 | — |
| SWE-bench Multilingual | 67.3% | — |
| SciCode | 49% | — |
| WeirdML | 45.6% | — |
| BigCodeBench Instruct | — | 33.9% |
| BigCodeBench Complete | — | 43.8% |
| ALE-Bench | 821.65 | — |
Agentic & Tool Use Not comparable
Kimi K2.5: 34.0 (#44), Yi-1.5-34B: —
| Benchmark | Kimi K2.5 | Yi-1.5-34B |
|---|---|---|
| Terminal-Bench | 43.2% | — |
| OSWorld | 63.3% | — |
| Vending-Bench 2 | 1,198 | — |
Reasoning Kimi K2.5 leads
Kimi K2.5: 31.2 (#74), Yi-1.5-34B: 21.5 (#195)
| Benchmark | Kimi K2.5 | Yi-1.5-34B |
|---|---|---|
| LMArena Hard Prompts | 1454 | 1160 |
| 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 | 148.05 | — |
Math Kimi K2.5 leads
Kimi K2.5: 50.3 (#46), Yi-1.5-34B: 25.3 (#248)
| Benchmark | Kimi K2.5 | Yi-1.5-34B |
|---|---|---|
| LMArena Math | 1470 | 1182 |
| MathArena Final-Answer Competitions | 62.3% | — |
| OTIS Mock AIME 2024-2025 | 92.2% | — |
| MATH Level 5 | — | 25.5% |
| FrontierMath (Feb 2025 set) | 27.9% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Kimi K2.5 leads
Kimi K2.5: 53.6 (#52), Yi-1.5-34B: 14.8 (#290)
| Benchmark | Kimi K2.5 | Yi-1.5-34B |
|---|---|---|
| GPQA Diamond | 87.6% | 32% |
| LMArena Expert | 1466 | 1144 |
| Humanity's Last Exam | 24.4% | — |
| SimpleQA Verified | 34.3% | — |
| Vectara Hallucination Rate | 14.2% | — |
Multimodal Not comparable
Kimi K2.5: 40.4 (#37), Yi-1.5-34B: —
| Benchmark | Kimi K2.5 | Yi-1.5-34B |
|---|---|---|
| LMArena Vision | 1269 | — |
| LMArena Document | 1430 | — |
Multilingual Kimi K2.5 leads
Kimi K2.5: 54.1 (#50), Yi-1.5-34B: 32.5 (#251)
| Benchmark | Kimi K2.5 | Yi-1.5-34B |
|---|---|---|
| LMArena Non-English | 1433 | 1121 |
| LMArena Chinese | 1495 | 1213 |
| LMArena French | 1454 | 1155 |
| LMArena German | 1441 | 1111 |
| LMArena Japanese | 1422 | 1021 |
| LMArena Korean | 1412 | 1005 |
| LMArena Russian | 1436 | 1091 |
| LMArena Spanish | 1450 | 1120 |
Instruction Following Kimi K2.5 leads
Kimi K2.5: 75.5 (#60), Yi-1.5-34B: 59.4 (#252)
| Benchmark | Kimi K2.5 | Yi-1.5-34B |
|---|---|---|
| LMArena Instruction Following | 1431 | 1139 |
Long Context Kimi K2.5 leads
Kimi K2.5: 52.1 (#7), Yi-1.5-34B: 34.6 (#243)
| Benchmark | Kimi K2.5 | Yi-1.5-34B |
|---|---|---|
| LMArena Longer Query | 1445 | 1144 |
| Fiction.LiveBench | 86.1% | — |
| CL-bench | 19.3% | — |
| CL-bench Life | 13.2% | — |
Writing & Preference Kimi K2.5 leads
Kimi K2.5: 65.3 (#51), Yi-1.5-34B: 37.6 (#252)
| Benchmark | Kimi K2.5 | Yi-1.5-34B |
|---|---|---|
| LMArena Text | 1445 | 1173 |
| LMArena Creative Writing | 1423 | 1135 |
| LMArena Multi-Turn | 1444 | 1153 |
| EQ-Bench Creative Writing | 1579 | — |
Frequently asked questions
Is Kimi K2.5 better than Yi-1.5-34B?
Kimi K2.5 is the stronger model overall, scoring 47.8 to 30.2 on the Noometry Index.
Is Kimi K2.5 or Yi-1.5-34B better for coding?
Kimi K2.5 scores higher on coding benchmarks: 48.7 versus 31.9 in the Noometry coding category.
How many benchmarks do Kimi K2.5 and Yi-1.5-34B share?
18 benchmarks have published results for both models. Kimi K2.5 has 51 scored results on Noometry and Yi-1.5-34B has 21.