Model comparison
Granite 3.1 2b Instruct vs Kimi K2.5
Kimi K2.5 is the stronger model overall, scoring 48.1 to 33.2 on the Noometry Index.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. Granite 3.1 2b Instruct scores higher in 0 categories and Kimi K2.5 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Kimi K2.5 leads 65.1 to 34.1.
Side by side
| Granite 3.1 2b Instruct | Kimi K2.5 | |
|---|---|---|
| Provider | IBM | Moonshot AI |
| Noometry Index | 33.2 | 48.1 |
| Released | — | 2026-01-27 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.45 |
| Output $ / M tokens | — | $2.25 |
| Results tracked | 12 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.5 leads
Granite 3.1 2b Instruct: 33.4 (#257), Kimi K2.5: 48.8 (#53)
| Benchmark | Granite 3.1 2b Instruct | Kimi K2.5 |
|---|---|---|
| LMArena Coding | 1149 | 1474 |
| 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
Granite 3.1 2b Instruct: —, Kimi K2.5: 34.2 (#48)
| Benchmark | Granite 3.1 2b Instruct | Kimi K2.5 |
|---|---|---|
| Terminal-Bench | — | 43.2% |
| OSWorld | — | 63.3% |
| Vending-Bench 2 | — | 1,198 |
Reasoning Kimi K2.5 leads
Granite 3.1 2b Instruct: 22.0 (#209), Kimi K2.5: 31.2 (#80)
| Benchmark | Granite 3.1 2b Instruct | Kimi K2.5 |
|---|---|---|
| LMArena Hard Prompts | 1138 | 1453 |
| 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
Granite 3.1 2b Instruct: 33.1 (#206), Kimi K2.5: 51.8 (#53)
| Benchmark | Granite 3.1 2b Instruct | Kimi K2.5 |
|---|---|---|
| LMArena Math | 1159 | 1470 |
| 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
Granite 3.1 2b Instruct: 30.8 (#224), Kimi K2.5: 53.6 (#56)
| Benchmark | Granite 3.1 2b Instruct | Kimi K2.5 |
|---|---|---|
| LMArena Expert | 1131 | 1466 |
| GPQA Diamond | — | 87.6% |
| Humanity's Last Exam | — | 24.4% |
| SimpleQA Verified | — | 34.3% |
| Vectara Hallucination Rate | — | 14.2% |
Multimodal Not comparable
Granite 3.1 2b Instruct: —, Kimi K2.5: 41.1 (#39)
| Benchmark | Granite 3.1 2b Instruct | Kimi K2.5 |
|---|---|---|
| LMArena Vision | — | 1269 |
| LMArena Document | — | 1430 |
Multilingual Kimi K2.5 leads
Granite 3.1 2b Instruct: 29.1 (#269), Kimi K2.5: 53.9 (#53)
| Benchmark | Granite 3.1 2b Instruct | Kimi K2.5 |
|---|---|---|
| LMArena Non-English | 1068 | 1433 |
| LMArena Chinese | 1139 | 1495 |
| LMArena Russian | 1063 | 1435 |
| LMArena French | — | 1454 |
| LMArena German | — | 1441 |
| LMArena Japanese | — | 1421 |
| LMArena Korean | — | 1410 |
| LMArena Spanish | — | 1450 |
Instruction Following Kimi K2.5 leads
Granite 3.1 2b Instruct: 57.7 (#264), Kimi K2.5: 75.3 (#64)
| Benchmark | Granite 3.1 2b Instruct | Kimi K2.5 |
|---|---|---|
| LMArena Instruction Following | 1116 | 1431 |
Long Context Kimi K2.5 leads
Granite 3.1 2b Instruct: 35.0 (#244), Kimi K2.5: 52.1 (#7)
| Benchmark | Granite 3.1 2b Instruct | Kimi K2.5 |
|---|---|---|
| LMArena Longer Query | 1155 | 1445 |
| Fiction.LiveBench | — | 86.1% |
| CL-bench | — | 19.3% |
| CL-bench Life | — | 13.2% |
Writing & Preference Kimi K2.5 leads
Granite 3.1 2b Instruct: 34.1 (#274), Kimi K2.5: 65.1 (#53)
| Benchmark | Granite 3.1 2b Instruct | Kimi K2.5 |
|---|---|---|
| LMArena Text | 1127 | 1445 |
| LMArena Creative Writing | 1116 | 1423 |
| LMArena Multi-Turn | 1099 | 1444 |
| EQ-Bench Creative Writing | — | 1579 |
Frequently asked questions
Is Granite 3.1 2b Instruct better than Kimi K2.5?
Kimi K2.5 is the stronger model overall, scoring 48.1 to 33.2 on the Noometry Index.
Is Granite 3.1 2b Instruct or Kimi K2.5 better for coding?
Kimi K2.5 scores higher on coding benchmarks: 48.8 versus 33.4 in the Noometry coding category.
How many benchmarks do Granite 3.1 2b Instruct and Kimi K2.5 share?
12 benchmarks have published results for both models. Granite 3.1 2b Instruct has 12 scored results on Noometry and Kimi K2.5 has 51.