Model comparison
GLM-5.1 vs Kimi K2.5
GLM-5.1 and Kimi K2.5 score almost the same on the Noometry Index (47.8 vs 48.1), so choose on price, context window or the category you care about most.
Last verified . 36 shared benchmarks.
Summary
- They share 36 benchmarks with published results for both. GLM-5.1 scores higher in 5 categories and Kimi K2.5 in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Kimi K2.5 leads 34.2 to 24.9.
- The biggest single-benchmark swing is WeirdML: 57.1% for GLM-5.1 and 45.6% for Kimi K2.5.
- Kimi K2.5 is cheaper at $0.45 / $2.25 per million input/output tokens, against $1.40 / $4.40 for GLM-5.1.
- Kimi K2.5 accepts more context: 262K tokens versus 200K.
Side by side
| GLM-5.1 | Kimi K2.5 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Moonshot AI |
| Noometry Index | 47.8 | 48.1 |
| Released | 2026-04-07 | 2026-01-27 |
| Weights | Open | Open |
| Context window | 200K | 262K |
| Max output | 131K | 262K |
| Input $ / M tokens | $1.40 | $0.45 |
| Output $ / M tokens | $4.40 | $2.25 |
| Results tracked | 41 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GLM-5.1: 48.7 (#55), Kimi K2.5: 48.8 (#53)
| Benchmark | GLM-5.1 | Kimi K2.5 |
|---|---|---|
| SWE-bench Verified | 74.2% | 73.8% |
| LMArena WebDev | 1508 | 1437 |
| SciCode | 43.8% | 49% |
| WeirdML | 57.1% | 45.6% |
| LMArena Coding | 1485 | 1474 |
| ALE-Bench | 887.1 | 821.65 |
| SWE-bench Verified (bash only) | — | 70.8% |
| SWE-bench Multilingual | — | 67.3% |
Agentic & Tool Use Kimi K2.5 leads
GLM-5.1: 24.9 (#113), Kimi K2.5: 34.2 (#48)
| Benchmark | GLM-5.1 | Kimi K2.5 |
|---|---|---|
| Vending-Bench 2 | 5,634 | 1,198 |
| Terminal-Bench | — | 43.2% |
| APEX-Agents | 40.9% | — |
| OSWorld | — | 63.3% |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
Reasoning GLM-5.1 leads
GLM-5.1: 39.1 (#60), Kimi K2.5: 31.2 (#80)
| Benchmark | GLM-5.1 | Kimi K2.5 |
|---|---|---|
| SimpleBench | 55.1% | 46.8% |
| NYT Connections (extended) | 77.7% | 69.9% |
| CritPt | 4.6% | 3.1% |
| Chess Puzzles | 19% | 12% |
| Thematic Generalization | 69.8% | 69.4% |
| LMArena Hard Prompts | 1472 | 1453 |
| Epoch Capabilities Index | 149.84 | 148.03 |
| ARC-AGI-2 | — | 11.8% |
| Kagi LLM Benchmark | — | 78.5% |
| ARC-AGI-1 | — | 65.3% |
| EnigmaEval | — | 3.4% |
Math Kimi K2.5 leads
GLM-5.1: 49.7 (#60), Kimi K2.5: 51.8 (#53)
| Benchmark | GLM-5.1 | Kimi K2.5 |
|---|---|---|
| MathArena Final-Answer Competitions | 67.1% | 62.3% |
| OTIS Mock AIME 2024-2025 | 93.3% | 92.2% |
| LMArena Math | 1473 | 1470 |
| FrontierMath (Feb 2025 set) | 33.4% | 27.9% |
| FrontierMath Tier 4 (v1) | 12.5% | 4.2% |
| FrontierMath (Tiers 1-3) | 36.8% | — |
| ProofBench | 22.2% | — |
Knowledge GLM-5.1 leads
GLM-5.1: 54.9 (#50), Kimi K2.5: 53.6 (#56)
| Benchmark | GLM-5.1 | Kimi K2.5 |
|---|---|---|
| GPQA Diamond | 89.9% | 87.6% |
| SimpleQA Verified | 34% | 34.3% |
| LMArena Expert | 1476 | 1466 |
| Humanity's Last Exam | — | 24.4% |
| Vectara Hallucination Rate | — | 14.2% |
Multimodal Not comparable
GLM-5.1: —, Kimi K2.5: 41.1 (#39)
| Benchmark | GLM-5.1 | Kimi K2.5 |
|---|---|---|
| LMArena Vision | — | 1269 |
| LMArena Document | — | 1430 |
Multilingual GLM-5.1 leads
GLM-5.1: 55.0 (#36), Kimi K2.5: 53.9 (#53)
| Benchmark | GLM-5.1 | Kimi K2.5 |
|---|---|---|
| LMArena Non-English | 1447 | 1433 |
| LMArena Chinese | 1515 | 1495 |
| LMArena French | 1474 | 1454 |
| LMArena German | 1465 | 1441 |
| LMArena Japanese | 1434 | 1421 |
| LMArena Korean | 1418 | 1410 |
| LMArena Russian | 1454 | 1435 |
| LMArena Spanish | 1469 | 1450 |
Instruction Following Too close to call
GLM-5.1: 76.3 (#42), Kimi K2.5: 75.3 (#64)
| Benchmark | GLM-5.1 | Kimi K2.5 |
|---|---|---|
| LMArena Instruction Following | 1451 | 1431 |
Long Context Kimi K2.5 leads
GLM-5.1: 44.9 (#53), Kimi K2.5: 52.1 (#7)
| Benchmark | GLM-5.1 | Kimi K2.5 |
|---|---|---|
| LMArena Longer Query | 1466 | 1445 |
| Fiction.LiveBench | — | 86.1% |
| CL-bench | — | 19.3% |
| CL-bench Life | — | 13.2% |
Writing & Preference GLM-5.1 leads
GLM-5.1: 66.9 (#31), Kimi K2.5: 65.1 (#53)
| Benchmark | GLM-5.1 | Kimi K2.5 |
|---|---|---|
| LMArena Text | 1461 | 1445 |
| LMArena Creative Writing | 1453 | 1423 |
| EQ-Bench Creative Writing | 1592 | 1579 |
| LMArena Multi-Turn | 1472 | 1444 |
Frequently asked questions
Is GLM-5.1 better than Kimi K2.5?
GLM-5.1 and Kimi K2.5 score almost the same on the Noometry Index (47.8 vs 48.1), so choose on price, context window or the category you care about most.
Which is cheaper, GLM-5.1 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-5.1 lists at $1.40 and $4.40.
Is GLM-5.1 or Kimi K2.5 better for coding?
They score almost the same on coding (48.7 vs 48.8); test both on your own repository before choosing.
Which has the bigger context window?
Kimi K2.5 does, with 262K tokens against 200K.
How many benchmarks do GLM-5.1 and Kimi K2.5 share?
36 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Kimi K2.5 has 51.