Model comparison
Grok-2 (Dec 2024) vs Kimi K2.5
Kimi K2.5 is the stronger model overall, scoring 48.1 to 33.7 on the Noometry Index.
Last verified . 23 shared benchmarks.
Summary
- They share 23 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 0 categories and Kimi K2.5 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2.5 leads 51.8 to 20.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 11.5% for Grok-2 (Dec 2024) and 92.2% for Kimi K2.5.
- Kimi K2.5 has downloadable open weights; the other is API-only.
Side by side
| Grok-2 (Dec 2024) | Kimi K2.5 | |
|---|---|---|
| Provider | xAI | Moonshot AI |
| Noometry Index | 33.7 | 48.1 |
| Released | 2024-08-13 | 2026-01-27 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.45 |
| Output $ / M tokens | — | $2.25 |
| Results tracked | 34 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.5 leads
Grok-2 (Dec 2024): 33.3 (#258), Kimi K2.5: 48.8 (#53)
| Benchmark | Grok-2 (Dec 2024) | Kimi K2.5 |
|---|---|---|
| WeirdML | 22.2% | 45.6% |
| LMArena Coding | 1287 | 1474 |
| SWE-bench Verified | — | 73.8% |
| SWE-bench Verified (bash only) | — | 70.8% |
| LMArena WebDev | — | 1437 |
| SWE-bench Multilingual | — | 67.3% |
| SciCode | — | 49% |
| LiveBench Coding | 46.4% | — |
| ALE-Bench | — | 821.65 |
Agentic & Tool Use Not comparable
Grok-2 (Dec 2024): —, Kimi K2.5: 34.2 (#48)
| Benchmark | Grok-2 (Dec 2024) | Kimi K2.5 |
|---|---|---|
| Terminal-Bench | — | 43.2% |
| OSWorld | — | 63.3% |
| Vending-Bench 2 | — | 1,198 |
Reasoning Kimi K2.5 leads
Grok-2 (Dec 2024): 16.9 (#299), Kimi K2.5: 31.2 (#80)
| Benchmark | Grok-2 (Dec 2024) | Kimi K2.5 |
|---|---|---|
| SimpleBench | 22.7% | 46.8% |
| LMArena Hard Prompts | 1272 | 1453 |
| Epoch Capabilities Index | 130.48 | 148.03 |
| ARC-AGI-2 | — | 11.8% |
| 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% |
| LiveBench Reasoning | 54.8% | — |
| DTBench | 65.2% | — |
| LiveBench Data Analysis | 54.5% | — |
| LiveBench | 54.3% | — |
Math Kimi K2.5 leads
Grok-2 (Dec 2024): 20.8 (#284), Kimi K2.5: 51.8 (#53)
| Benchmark | Grok-2 (Dec 2024) | Kimi K2.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 11.5% | 92.2% |
| LMArena Math | 1283 | 1470 |
| FrontierMath (Feb 2025 set) | 0.7% | 27.9% |
| MathArena Final-Answer Competitions | — | 62.3% |
| LiveBench Math | 54.9% | — |
| MATH Level 5 | 63.5% | — |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Kimi K2.5 leads
Grok-2 (Dec 2024): 29.8 (#233), Kimi K2.5: 53.6 (#56)
| Benchmark | Grok-2 (Dec 2024) | Kimi K2.5 |
|---|---|---|
| GPQA Diamond | 53.8% | 87.6% |
| LMArena Expert | 1254 | 1466 |
| Humanity's Last Exam | — | 24.4% |
| SimpleQA Verified | — | 34.3% |
| Confabulations | 20.1% | — |
| Vectara Hallucination Rate | — | 14.2% |
Multimodal Not comparable
Grok-2 (Dec 2024): —, Kimi K2.5: 41.1 (#39)
| Benchmark | Grok-2 (Dec 2024) | Kimi K2.5 |
|---|---|---|
| LMArena Vision | — | 1269 |
| LMArena Document | — | 1430 |
Multilingual Kimi K2.5 leads
Grok-2 (Dec 2024): 43.1 (#188), Kimi K2.5: 53.9 (#53)
| Benchmark | Grok-2 (Dec 2024) | Kimi K2.5 |
|---|---|---|
| LMArena Non-English | 1282 | 1433 |
| LMArena Chinese | 1289 | 1495 |
| LMArena French | 1318 | 1454 |
| LMArena German | 1287 | 1441 |
| LMArena Japanese | 1244 | 1421 |
| LMArena Korean | 1237 | 1410 |
| LMArena Russian | 1286 | 1435 |
| LMArena Spanish | 1281 | 1450 |
Instruction Following Kimi K2.5 leads
Grok-2 (Dec 2024): 66.9 (#202), Kimi K2.5: 75.3 (#64)
| Benchmark | Grok-2 (Dec 2024) | Kimi K2.5 |
|---|---|---|
| LMArena Instruction Following | 1270 | 1431 |
| LiveBench Instruction Following | 69.6% | — |
Long Context Kimi K2.5 leads
Grok-2 (Dec 2024): 38.8 (#190), Kimi K2.5: 52.1 (#7)
| Benchmark | Grok-2 (Dec 2024) | Kimi K2.5 |
|---|---|---|
| LMArena Longer Query | 1276 | 1445 |
| Fiction.LiveBench | — | 86.1% |
| CL-bench | — | 19.3% |
| CL-bench Life | — | 13.2% |
Writing & Preference Kimi K2.5 leads
Grok-2 (Dec 2024): 48.6 (#198), Kimi K2.5: 65.1 (#53)
| Benchmark | Grok-2 (Dec 2024) | Kimi K2.5 |
|---|---|---|
| LMArena Text | 1305 | 1445 |
| LMArena Creative Writing | 1284 | 1423 |
| LMArena Multi-Turn | 1290 | 1444 |
| Short-Story Creative Writing | 63.6% | — |
| EQ-Bench Creative Writing | — | 1579 |
| LiveBench Language | 45.6% | — |
Frequently asked questions
Is Grok-2 (Dec 2024) better than Kimi K2.5?
Kimi K2.5 is the stronger model overall, scoring 48.1 to 33.7 on the Noometry Index.
Is Grok-2 (Dec 2024) or Kimi K2.5 better for coding?
Kimi K2.5 scores higher on coding benchmarks: 48.8 versus 33.3 in the Noometry coding category.
How many benchmarks do Grok-2 (Dec 2024) and Kimi K2.5 share?
23 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and Kimi K2.5 has 51.