Side-by-side comparison · models
GLM 5.1 TEE vs Kimi K2.5 TEE
What we have checked about each, line by line. Every value shows where it came from and when we last confirmed it.
Models
GLM 5.1 TEE
Flagship GLM model for hybrid reasoning, coding, and agentic engineering.
Models
Kimi K2.5 TEE
Kimi model for long-context chat, coding, and agentic reasoning.
Checked facts
Line by line
| Measure | GLM 5.1 TEE | Kimi K2.5 TEE |
|---|---|---|
| Input price | $1.33 per million tokens | $0.532 per million tokens |
| Output price | $4.18 per million tokens | $3.33 per million tokens |
| Price on atlas-cloud | $0.234 per million cached input tokens | $0.200 per million cached input tokens |
| Price on atlas-cloud | $1.26 per million input tokens | $0.490 per million input tokens |
| Price on atlas-cloud | $3.96 per million output tokens | $2.50 per million output tokens |
| Price on baidu | $0.260 per million cached input tokens | Not checked yet |
| Price on baidu | $1.40 per million input tokens | Not checked yet |
| Price on baidu | $4.40 per million output tokens | Not checked yet |
| Price on chutes | $0.090 per million cached input tokens | Not checked yet |
| Price on chutes | $0.900 per million input tokens | Not checked yet |
| Price on chutes | $2.90 per million output tokens | Not checked yet |
| Price on friendli | $0.260 per million cached input tokens | Not checked yet |
| Price on friendli | $1.40 per million input tokens | Not checked yet |
| Price on friendli | $4.40 per million output tokens | Not checked yet |
| Price on gmicloud | $0.260 per million cached input tokens | Not checked yet |
| Price on gmicloud | $1.40 per million input tokens | Not checked yet |
| Price on gmicloud | $4.40 per million output tokens | Not checked yet |
| Price on nebius | $0.260 per million cached input tokens | Not checked yet |
| Price on nebius | $1.40 per million input tokens | Not checked yet |
| Price on nebius | $4.40 per million output tokens | Not checked yet |
| Price on novita | $0.260 per million cached input tokens | $0.095 per million cached input tokens |
| Price on novita | $1.38 per million input tokens | $0.570 per million input tokens |
| Price on novita | $4.40 per million output tokens | $2.85 per million output tokens |
| Price on phala | $0.600 per million cached input tokens | Not checked yet |
| Price on phala | $1.21 per million input tokens | Not checked yet |
| Price on phala | $4.20 per million output tokens | Not checked yet |
| Price on qwen | $0.247 per million cached input tokens | Not checked yet |
| Price on qwen | $1.33 per million input tokens | Not checked yet |
| Price on qwen | $4.18 per million output tokens | Not checked yet |
| Price on siliconflow | $0.600 per million cached input tokens | $0.150 per million cached input tokens |
| Price on siliconflow | $1.19 per million input tokens | $0.500 per million input tokens |
| Price on siliconflow | $3.74 per million output tokens | $2.50 per million output tokens |
| Price on streamlake | $0.179 per million cached input tokens | Not checked yet |
| Price on streamlake | $0.966 per million input tokens | Not checked yet |
| Price on streamlake | $3.04 per million output tokens | Not checked yet |
| Price on venice | $0.260 per million cached input tokens | $0.209 per million cached input tokens |
| Price on venice | $1.40 per million input tokens | $0.532 per million input tokens |
| Price on venice | $4.40 per million output tokens | $3.33 per million output tokens |
| Price on z-ai | $0.260 per million cached input tokens | Not checked yet |
| Price on z-ai | $1.40 per million input tokens | Not checked yet |
| Price on z-ai | $4.40 per million output tokens | Not checked yet |
| Price on amazon-bedrock | Not checked yet | $0.600 per million input tokens |
| Price on amazon-bedrock | Not checked yet | $3.00 per million output tokens |
| Latest version | z-ai/glm-5.1-20260406 | moonshotai/kimi-k2.5-0127 |
| Time to first token (ms) | 1,420 | 1,780 |
| Time to first token (ms) on atlas-cloud | 2,307 | 817 |
| Time to first token (ms) on baidu | 1,076 | Not checked yet |
| Time to first token (ms) on chutes | 1,535 | Not checked yet |
| Time to first token (ms) on friendli | 497 | Not checked yet |
| Time to first token (ms) on gmicloud | 1,781 | Not checked yet |
| Time to first token (ms) on nebius | 810 | Not checked yet |
| Time to first token (ms) on novita | 5,758 | 1,374 |
| Time to first token (ms) on phala | 3,769 | Not checked yet |
| Time to first token (ms) on qwen | 855 | Not checked yet |
| Time to first token (ms) on siliconflow | 1,300 | 1,549 |
| Time to first token (ms) on streamlake | 3,010 | Not checked yet |
| Time to first token (ms) on venice | 939 | 1,011 |
| Time to first token (ms) on z-ai | 3,934 | Not checked yet |
| Output speed (tokens a second) | 81.5 | 45.4 |
| Output speed (tokens a second) on atlas-cloud | 49.5 | 45 |
| Output speed (tokens a second) on baidu | 78 | Not checked yet |
| Output speed (tokens a second) on chutes | 37 | Not checked yet |
| Output speed (tokens a second) on friendli | 91 | Not checked yet |
| Output speed (tokens a second) on gmicloud | 51 | Not checked yet |
| Output speed (tokens a second) on nebius | 30 | Not checked yet |
| Output speed (tokens a second) on novita | 27.5 | 38 |
| Output speed (tokens a second) on phala | 23.5 | Not checked yet |
| Output speed (tokens a second) on qwen | 71 | Not checked yet |
| Output speed (tokens a second) on siliconflow | 58 | 22 |
| Output speed (tokens a second) on streamlake | 27 | Not checked yet |
| Output speed (tokens a second) on venice | 58 | 22 |
| Output speed (tokens a second) on z-ai | 26 | Not checked yet |
| Time to first token (ms) on amazon-bedrock | Not checked yet | 1,140 |
| Output speed (tokens a second) on amazon-bedrock | Not checked yet | 52 |
| Tokens served on OpenRouter in a day | 2.7B (for 10 Nov 2026) | 3.8B (for 10 Nov 2026) |
| Tool calls on OpenRouter in a day | 20.6K (for 10 Nov 2026) | 46.7K (for 10 Nov 2026) |
| Artificial Analysis Intelligence Index | 26.1 | 23.5 |
| Artificial Analysis Coding Index | 55.8 | 46.8 |
| Artificial Analysis Agentic Index | 23.9 | Not checked yet |
| LMArena text rating (Elo) | 1,463 | 1,445 |
| LMArena web development rating (Elo) | 1,508 | 1,436 |
| Design Arena rating (Elo) | 1,366 | 1,245 |
| Gpqa diamond | 89.9% (for 7 Apr 2026) | Not checked yet |
| Swe bench verified | 74.2% (for 7 Apr 2026) | Not checked yet |
| Frontiermath tiers 1 3 v2 private | 36.8% (for 7 Apr 2026) | Not checked yet |
| Simpleqa verified | 34% (for 7 Apr 2026) | Not checked yet |
| Apex agents | 40.9% (for 7 Apr 2026) | Not checked yet |
| Chess puzzles | 20% (for 7 Apr 2026) | Not checked yet |
| Exploitbench | 18.1% (for 7 Apr 2026) | Not checked yet |
| Frontiermath 2025 02 28 private | 33.4% (for 7 Apr 2026) | Not checked yet |
| Frontiermath tier 4 2025 07 01 private | 12.5% (for 7 Apr 2026) | Not checked yet |
| Proofbench | 22.2% (for 7 Apr 2026) | Not checked yet |
| Simplebench | 55.1% (for 7 Apr 2026) | Not checked yet |
| Weirdml | 57.1% (for 7 Apr 2026) | Not checked yet |
| Otis mock aime 2024 2025 | 93.3% (saturated benchmark: the top models all score near the ceiling) (for 7 Apr 2026) | Not checked yet |
| LMArena vision rating (Elo) | Not checked yet | 1,269 |
A line appears only when at least one record has a value we confirmed from a source. Values we have not confirmed are left out, never guessed. Records of different types share fewer lines.
Add a third
Compare with one more record
How this works
Share it, or build your own
This page works for any two or three records in the directory, of any type. The link stays the same whichever order you name them in, so you can share it as it is. Change the records in the address, for example /directories/vs/claude-code-vs-cursor, or start from our editorial comparisons.