Model comparison
GLM-4.7 vs Kimi K2.5
Kimi K2.5 is the stronger model overall, scoring 48.1 to 42.0 on the Noometry Index.
Last verified . 35 shared benchmarks.
Summary
- They share 35 benchmarks with published results for both. GLM-4.7 scores higher in 0 categories and Kimi K2.5 in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2.5 leads 51.8 to 38.6.
- The biggest single-benchmark swing is Terminal-Bench: 33.4% for GLM-4.7 and 43.2% for Kimi K2.5.
- Kimi K2.5 is cheaper at $0.45 / $2.25 per million input/output tokens, against $0.60 / $2.20 for GLM-4.7.
- Kimi K2.5 accepts more context: 262K tokens versus 205K.
Side by side
| GLM-4.7 | Kimi K2.5 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Moonshot AI |
| Noometry Index | 42.0 | 48.1 |
| Released | 2025-12-22 | 2026-01-27 |
| Weights | Open | Open |
| Context window | 205K | 262K |
| Max output | 131K | 262K |
| Input $ / M tokens | $0.60 | $0.45 |
| Output $ / M tokens | $2.20 | $2.25 |
| Results tracked | 36 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.5 leads
GLM-4.7: 44.0 (#79), Kimi K2.5: 48.8 (#53)
| Benchmark | GLM-4.7 | Kimi K2.5 |
|---|---|---|
| LMArena WebDev | 1435 | 1437 |
| SciCode | 45.1% | 49% |
| LMArena Coding | 1454 | 1474 |
| ALE-Bench | 399.48 | 821.65 |
| SWE-bench Verified | — | 73.8% |
| SWE-bench Verified (bash only) | — | 70.8% |
| SWE-bench Multilingual | — | 67.3% |
| WeirdML | — | 45.6% |
Agentic & Tool Use Kimi K2.5 leads
GLM-4.7: 26.5 (#103), Kimi K2.5: 34.2 (#48)
| Benchmark | GLM-4.7 | Kimi K2.5 |
|---|---|---|
| Terminal-Bench | 33.4% | 43.2% |
| Vending-Bench 2 | 2,377 | 1,198 |
| OSWorld | — | 63.3% |
Reasoning Kimi K2.5 leads
GLM-4.7: 24.3 (#164), Kimi K2.5: 31.2 (#80)
| Benchmark | GLM-4.7 | Kimi K2.5 |
|---|---|---|
| SimpleBench | 47.7% | 46.8% |
| CritPt | 1.7% | 3.1% |
| Chess Puzzles | 6% | 12% |
| LMArena Hard Prompts | 1443 | 1453 |
| Epoch Capabilities Index | 143.51 | 148.03 |
| ARC-AGI-2 | — | 11.8% |
| Kagi LLM Benchmark | — | 78.5% |
| NYT Connections (extended) | — | 69.9% |
| ARC-AGI-1 | — | 65.3% |
| EnigmaEval | — | 3.4% |
| Thematic Generalization | — | 69.4% |
Math Kimi K2.5 leads
GLM-4.7: 38.6 (#135), Kimi K2.5: 51.8 (#53)
| Benchmark | GLM-4.7 | Kimi K2.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 83.3% | 92.2% |
| LMArena Math | 1423 | 1470 |
| FrontierMath (Feb 2025 set) | 2.4% | 27.9% |
| FrontierMath Tier 4 (v1) | 0% | 4.2% |
| MathArena Final-Answer Competitions | — | 62.3% |
| ProofBench | 6% | — |
Knowledge Kimi K2.5 leads
GLM-4.7: 47.0 (#80), Kimi K2.5: 53.6 (#56)
| Benchmark | GLM-4.7 | Kimi K2.5 |
|---|---|---|
| GPQA Diamond | 83.3% | 87.6% |
| SimpleQA Verified | 32.2% | 34.3% |
| Vectara Hallucination Rate | 11.7% | 14.2% |
| LMArena Expert | 1424 | 1466 |
| Humanity's Last Exam | — | 24.4% |
Multimodal Not comparable
GLM-4.7: —, Kimi K2.5: 41.1 (#39)
| Benchmark | GLM-4.7 | Kimi K2.5 |
|---|---|---|
| LMArena Vision | — | 1269 |
| LMArena Document | — | 1430 |
Multilingual Kimi K2.5 leads
GLM-4.7: 52.8 (#79), Kimi K2.5: 53.9 (#53)
| Benchmark | GLM-4.7 | Kimi K2.5 |
|---|---|---|
| LMArena Non-English | 1417 | 1433 |
| LMArena Chinese | 1495 | 1495 |
| LMArena French | 1432 | 1454 |
| LMArena German | 1424 | 1441 |
| LMArena Japanese | 1439 | 1421 |
| LMArena Korean | 1399 | 1410 |
| LMArena Russian | 1423 | 1435 |
| LMArena Spanish | 1434 | 1450 |
Instruction Following Too close to call
GLM-4.7: 74.4 (#95), Kimi K2.5: 75.3 (#64)
| Benchmark | GLM-4.7 | Kimi K2.5 |
|---|---|---|
| LMArena Instruction Following | 1411 | 1431 |
Long Context Kimi K2.5 leads
GLM-4.7: 42.8 (#116), Kimi K2.5: 52.1 (#7)
| Benchmark | GLM-4.7 | Kimi K2.5 |
|---|---|---|
| CL-bench | 15.9% | 19.3% |
| CL-bench Life | 10.9% | 13.2% |
| LMArena Longer Query | 1432 | 1445 |
| Fiction.LiveBench | — | 86.1% |
Writing & Preference Kimi K2.5 leads
GLM-4.7: 60.9 (#93), Kimi K2.5: 65.1 (#53)
| Benchmark | GLM-4.7 | Kimi K2.5 |
|---|---|---|
| LMArena Text | 1435 | 1445 |
| LMArena Creative Writing | 1401 | 1423 |
| EQ-Bench Creative Writing | 1413 | 1579 |
| LMArena Multi-Turn | 1446 | 1444 |
Frequently asked questions
Is GLM-4.7 better than Kimi K2.5?
Kimi K2.5 is the stronger model overall, scoring 48.1 to 42.0 on the Noometry Index.
Which is cheaper, GLM-4.7 or Kimi K2.5?
Kimi K2.5 is cheaper. It lists at $0.45 per million input tokens and $2.25 per million output tokens; GLM-4.7 lists at $0.60 and $2.20.
Is GLM-4.7 or Kimi K2.5 better for coding?
Kimi K2.5 scores higher on coding benchmarks: 48.8 versus 44.0 in the Noometry coding category.
Which has the bigger context window?
Kimi K2.5 does, with 262K tokens against 205K.
How many benchmarks do GLM-4.7 and Kimi K2.5 share?
35 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Kimi K2.5 has 51.