Model comparison
GLM-5.1 vs Kimi K2 (Jul 2025)
GLM-5.1 is the stronger model overall, scoring 47.6 to 40.9 on the Noometry Index. Kimi K2 (Jul 2025) costs 2.1× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.
Last verified . 24 shared benchmarks.
Summary
- They share 24 benchmarks with published results for both. GLM-5.1 scores higher in 8 categories and Kimi K2 (Jul 2025) in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5.1 leads 55.0 to 36.9.
- The biggest single-benchmark swing is SimpleBench: 55.1% for GLM-5.1 and 26.3% for Kimi K2 (Jul 2025).
- Kimi K2 (Jul 2025) is cheaper at $0.57 / $2.30 per million input/output tokens, against $1.40 / $4.40 for GLM-5.1.
- Kimi K2 (Jul 2025) accepts more context: 262K tokens versus 200K.
Side by side
| GLM-5.1 | Kimi K2 (Jul 2025) | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Moonshot AI |
| Noometry Index | 47.6 | 40.9 |
| Released | 2026-04-07 | 2025-07-12 |
| Weights | Open | Open |
| Context window | 200K | 262K |
| Max output | 131K | 262K |
| Input $ / M tokens | $1.40 | $0.57 |
| Output $ / M tokens | $4.40 | $2.30 |
| Results tracked | 41 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.1 leads
GLM-5.1: 48.5 (#52), Kimi K2 (Jul 2025): 43.1 (#83)
| Benchmark | GLM-5.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| WeirdML | 57.1% | 42.8% |
| LMArena Coding | 1486 | 1399 |
| ALE-Bench | 887.1 | 597.5 |
| SWE-bench Verified | 74.2% | — |
| SWE-bench Verified (bash only) | — | 63.4% |
| Aider Polyglot | — | 59.1% |
| LMArena WebDev | 1509 | — |
| SciCode | 43.8% | — |
| GSO | — | 4.9% |
Agentic & Tool Use Kimi K2 (Jul 2025) leads
GLM-5.1: 24.8 (#106), Kimi K2 (Jul 2025): 32.2 (#59)
| Benchmark | GLM-5.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| Terminal-Bench | — | 35.7% |
| APEX-Agents | 40.9% | — |
| Berkeley Function Calling Leaderboard | — | 59.1% |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| METR Time Horizons | — | 59.2% |
| Vending-Bench 2 | 5,634 | — |
Reasoning GLM-5.1 leads
GLM-5.1: 38.2 (#57), Kimi K2 (Jul 2025): 22.7 (#173)
| Benchmark | GLM-5.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| SimpleBench | 55.1% | 26.3% |
| LMArena Hard Prompts | 1472 | 1384 |
| Epoch Capabilities Index | 149.86 | 146.02 |
| Kagi LLM Benchmark | — | 64.4% |
| NYT Connections (extended) | 77.7% | — |
| CritPt | 4.6% | — |
| Chess Puzzles | 19% | — |
| Thematic Generalization | 69.8% | — |
| ForecastBench | — | 60.2 |
Math GLM-5.1 leads
GLM-5.1: 49.0 (#48), Kimi K2 (Jul 2025): 40.1 (#81)
| Benchmark | GLM-5.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Math | 1472 | 1396 |
| FrontierMath (Feb 2025 set) | 33.4% | 21.4% |
| FrontierMath Tier 4 (v1) | 12.5% | 0% |
| FrontierMath (Tiers 1-3) | 36.8% | — |
| MathArena Final-Answer Competitions | 67.1% | — |
| OTIS Mock AIME 2024-2025 | 93.3% | — |
| ProofBench | 22.2% | — |
| Omni-MATH | — | 65.4% |
Knowledge GLM-5.1 leads
GLM-5.1: 55.0 (#45), Kimi K2 (Jul 2025): 36.9 (#153)
| Benchmark | GLM-5.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Expert | 1477 | 1363 |
| GPQA Diamond | 89.9% | — |
| SimpleQA Verified | 34% | — |
| MMLU-Pro | — | 81.9% |
| Confabulations | — | 20.4% |
| Vectara Hallucination Rate | — | 17.9% |
| GPQA (HELM) | — | 65.3% |
Multilingual GLM-5.1 leads
GLM-5.1: 55.2 (#34), Kimi K2 (Jul 2025): 49.8 (#125)
| Benchmark | GLM-5.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Non-English | 1448 | 1372 |
| LMArena Chinese | 1516 | 1416 |
| LMArena French | 1478 | 1379 |
| LMArena German | 1466 | 1386 |
| LMArena Japanese | 1436 | 1349 |
| LMArena Korean | 1423 | 1324 |
| LMArena Russian | 1453 | 1384 |
| LMArena Spanish | 1467 | 1383 |
Instruction Following GLM-5.1 leads
GLM-5.1: 76.5 (#41), Kimi K2 (Jul 2025): 71.3 (#151)
| Benchmark | GLM-5.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Instruction Following | 1451 | 1347 |
| IFEval | — | 85% |
Long Context GLM-5.1 leads
GLM-5.1: 44.9 (#51), Kimi K2 (Jul 2025): 41.2 (#140)
| Benchmark | GLM-5.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Longer Query | 1467 | 1353 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 17.6% |
Writing & Preference GLM-5.1 leads
GLM-5.1: 67.2 (#29), Kimi K2 (Jul 2025): 62.5 (#76)
| Benchmark | GLM-5.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Text | 1462 | 1380 |
| LMArena Creative Writing | 1454 | 1349 |
| EQ-Bench Creative Writing | 1592 | 1666 |
| LMArena Multi-Turn | 1473 | 1371 |
| Short-Story Creative Writing | — | 85.6% |
| WildBench | — | 86.2% |
Frequently asked questions
Is GLM-5.1 better than Kimi K2 (Jul 2025)?
GLM-5.1 is the stronger model overall, scoring 47.6 to 40.9 on the Noometry Index. Kimi K2 (Jul 2025) costs 2.1× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.
Which is cheaper, GLM-5.1 or Kimi K2 (Jul 2025)?
Kimi K2 (Jul 2025) is cheaper. It lists at $0.57 per million input tokens and $2.30 per million output tokens; GLM-5.1 lists at $1.40 and $4.40.
Is GLM-5.1 or Kimi K2 (Jul 2025) better for coding?
GLM-5.1 scores higher on coding benchmarks: 48.5 versus 43.1 in the Noometry coding category.
Which has the bigger context window?
Kimi K2 (Jul 2025) does, with 262K tokens against 200K.
How many benchmarks do GLM-5.1 and Kimi K2 (Jul 2025) share?
24 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Kimi K2 (Jul 2025) has 42.