Model comparison
Kimi K2.5 vs Tulu 3 (Tülu 3) 70B
Kimi K2.5 is the stronger model overall, scoring 48.1 to 33.0 on the Noometry Index.
Last verified . 13 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- They share 13 benchmarks with published results for both. Kimi K2.5 scores higher in 8 categories and Tulu 3 (Tülu 3) 70B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2.5 leads 51.8 to 14.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 92.2% for Kimi K2.5 and 4.4% for Tulu 3 (Tülu 3) 70B.
Side by side
| Kimi K2.5 | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Moonshot AI | Allen Institute for AI (Ai2) |
| Noometry Index | 48.1 | 33.0 |
| Released | 2026-01-27 | 2024-11-21 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 262K | — |
| Input $ / M tokens | $0.45 | — |
| Output $ / M tokens | $2.25 | — |
| Results tracked | 51 | 14 |
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), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | Kimi K2.5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1474 | 1235 |
| SWE-bench Verified | 73.8% | — |
| SWE-bench Verified (bash only) | 70.8% | — |
| LMArena WebDev | 1437 | — |
| 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), Tulu 3 (Tülu 3) 70B: —
| Benchmark | Kimi K2.5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| Terminal-Bench | 43.2% | — |
| OSWorld | 63.3% | — |
| Vending-Bench 2 | 1,198 | — |
Reasoning Kimi K2.5 leads
Kimi K2.5: 31.2 (#80), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | Kimi K2.5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1453 | 1220 |
| 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), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | Kimi K2.5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 92.2% | 4.4% |
| LMArena Math | 1470 | 1242 |
| MathArena Final-Answer Competitions | 62.3% | — |
| MATH Level 5 | — | 42.7% |
| FrontierMath (Feb 2025 set) | 27.9% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Kimi K2.5 leads
Kimi K2.5: 53.6 (#56), Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | Kimi K2.5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | 87.6% | 46.3% |
| Humanity's Last Exam | 24.4% | — |
| SimpleQA Verified | 34.3% | — |
| Vectara Hallucination Rate | 14.2% | — |
| LMArena Expert | 1466 | — |
Multimodal Not comparable
Kimi K2.5: 41.1 (#39), Tulu 3 (Tülu 3) 70B: —
| Benchmark | Kimi K2.5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Vision | 1269 | — |
| LMArena Document | 1430 | — |
Multilingual Kimi K2.5 leads
Kimi K2.5: 53.9 (#53), Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | Kimi K2.5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1433 | 1236 |
| LMArena Chinese | 1495 | 1249 |
| LMArena Russian | 1435 | 1246 |
| LMArena French | 1454 | — |
| LMArena German | 1441 | — |
| LMArena Japanese | 1421 | — |
| LMArena Korean | 1410 | — |
| LMArena Spanish | 1450 | — |
Instruction Following Kimi K2.5 leads
Kimi K2.5: 75.3 (#64), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | Kimi K2.5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1431 | 1233 |
Long Context Kimi K2.5 leads
Kimi K2.5: 52.1 (#7), Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | Kimi K2.5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1445 | 1224 |
| 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), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | Kimi K2.5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1445 | 1256 |
| LMArena Creative Writing | 1423 | 1231 |
| LMArena Multi-Turn | 1444 | 1252 |
| EQ-Bench Creative Writing | 1579 | — |
Frequently asked questions
Is Kimi K2.5 better than Tulu 3 (Tülu 3) 70B?
Kimi K2.5 is the stronger model overall, scoring 48.1 to 33.0 on the Noometry Index.
Is Kimi K2.5 or Tulu 3 (Tülu 3) 70B better for coding?
Kimi K2.5 scores higher on coding benchmarks: 48.8 versus 36.0 in the Noometry coding category.
How many benchmarks do Kimi K2.5 and Tulu 3 (Tülu 3) 70B share?
13 benchmarks have published results for both models. Kimi K2.5 has 51 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.