Side-by-side comparison · models
Gemma 4 31B vs GLM 5.1 TEE
What we have checked about each, line by line. Every value shows where it came from and when we last confirmed it.
Models
Gemma 4 31B
Open Gemma instruction model for efficient chat and self-hosted deployments.
Models
GLM 5.1 TEE
Flagship GLM model for hybrid reasoning, coding, and agentic engineering.
Checked facts
Line by line
| Measure | Gemma 4 31B | GLM 5.1 TEE |
|---|---|---|
| Input price | Not checked yet | $1.33 per million tokens |
| Output price | Not checked yet | $4.18 per million tokens |
| Price on atlas-cloud | Not checked yet | $0.234 per million cached input tokens |
| Price on atlas-cloud | Not checked yet | $1.26 per million input tokens |
| Price on atlas-cloud | Not checked yet | $3.96 per million output tokens |
| Price on baidu | Not checked yet | $0.260 per million cached input tokens |
| Price on baidu | Not checked yet | $1.40 per million input tokens |
| Price on baidu | Not checked yet | $4.40 per million output tokens |
| Price on chutes | Not checked yet | $0.090 per million cached input tokens |
| Price on chutes | Not checked yet | $0.900 per million input tokens |
| Price on chutes | Not checked yet | $2.90 per million output tokens |
| Price on friendli | Not checked yet | $0.260 per million cached input tokens |
| Price on friendli | Not checked yet | $1.40 per million input tokens |
| Price on friendli | Not checked yet | $4.40 per million output tokens |
| Price on gmicloud | Not checked yet | $0.260 per million cached input tokens |
| Price on gmicloud | Not checked yet | $1.40 per million input tokens |
| Price on gmicloud | Not checked yet | $4.40 per million output tokens |
| Price on nebius | Not checked yet | $0.260 per million cached input tokens |
| Price on nebius | Not checked yet | $1.40 per million input tokens |
| Price on nebius | Not checked yet | $4.40 per million output tokens |
| Price on novita | Not checked yet | $0.260 per million cached input tokens |
| Price on novita | Not checked yet | $1.38 per million input tokens |
| Price on novita | Not checked yet | $4.40 per million output tokens |
| Price on phala | Not checked yet | $0.600 per million cached input tokens |
| Price on phala | Not checked yet | $1.21 per million input tokens |
| Price on phala | Not checked yet | $4.20 per million output tokens |
| Price on qwen | Not checked yet | $0.247 per million cached input tokens |
| Price on qwen | Not checked yet | $1.33 per million input tokens |
| Price on qwen | Not checked yet | $4.18 per million output tokens |
| Price on siliconflow | Not checked yet | $0.600 per million cached input tokens |
| Price on siliconflow | Not checked yet | $1.19 per million input tokens |
| Price on siliconflow | Not checked yet | $3.74 per million output tokens |
| Price on streamlake | Not checked yet | $0.179 per million cached input tokens |
| Price on streamlake | Not checked yet | $0.966 per million input tokens |
| Price on streamlake | Not checked yet | $3.04 per million output tokens |
| Price on venice | Not checked yet | $0.260 per million cached input tokens |
| Price on venice | Not checked yet | $1.40 per million input tokens |
| Price on venice | Not checked yet | $4.40 per million output tokens |
| Price on z-ai | Not checked yet | $0.260 per million cached input tokens |
| Price on z-ai | Not checked yet | $1.40 per million input tokens |
| Price on z-ai | Not checked yet | $4.40 per million output tokens |
| Latest version | Not checked yet | z-ai/glm-5.1-20260406 |
| Time to first token (ms) | 1,100 | 1,420 |
| Output speed (tokens a second) | 34.7 | 81.5 |
| Time to first token (ms) on atlas-cloud | Not checked yet | 2,307 |
| Time to first token (ms) on baidu | Not checked yet | 1,076 |
| Time to first token (ms) on chutes | Not checked yet | 1,535 |
| Time to first token (ms) on friendli | Not checked yet | 497 |
| Time to first token (ms) on gmicloud | Not checked yet | 1,781 |
| Time to first token (ms) on nebius | Not checked yet | 810 |
| Time to first token (ms) on novita | Not checked yet | 5,758 |
| Time to first token (ms) on phala | Not checked yet | 3,769 |
| Time to first token (ms) on qwen | Not checked yet | 855 |
| Time to first token (ms) on siliconflow | Not checked yet | 1,300 |
| Time to first token (ms) on streamlake | Not checked yet | 3,010 |
| Time to first token (ms) on venice | Not checked yet | 939 |
| Time to first token (ms) on z-ai | Not checked yet | 3,934 |
| Output speed (tokens a second) on atlas-cloud | Not checked yet | 49.5 |
| Output speed (tokens a second) on baidu | Not checked yet | 78 |
| Output speed (tokens a second) on chutes | Not checked yet | 37 |
| Output speed (tokens a second) on friendli | Not checked yet | 91 |
| Output speed (tokens a second) on gmicloud | Not checked yet | 51 |
| Output speed (tokens a second) on nebius | Not checked yet | 30 |
| Output speed (tokens a second) on novita | Not checked yet | 27.5 |
| Output speed (tokens a second) on phala | Not checked yet | 23.5 |
| Output speed (tokens a second) on qwen | Not checked yet | 71 |
| Output speed (tokens a second) on siliconflow | Not checked yet | 58 |
| Output speed (tokens a second) on streamlake | Not checked yet | 27 |
| Output speed (tokens a second) on venice | Not checked yet | 58 |
| Output speed (tokens a second) on z-ai | Not checked yet | 26 |
| Tokens served on OpenRouter in a day | Not checked yet | 2.7B (for 10 Nov 2026) |
| Tool calls on OpenRouter in a day | Not checked yet | 20.6K (for 10 Nov 2026) |
| Artificial Analysis Intelligence Index | Not checked yet | 26.1 |
| Artificial Analysis Coding Index | Not checked yet | 55.8 |
| Artificial Analysis Agentic Index | Not checked yet | 23.9 |
| LMArena text rating (Elo) | Not checked yet | 1,463 |
| LMArena web development rating (Elo) | Not checked yet | 1,508 |
| Design Arena rating (Elo) | Not checked yet | 1,366 |
| Gpqa diamond | Not checked yet | 89.9% (for 7 Apr 2026) |
| Swe bench verified | Not checked yet | 74.2% (for 7 Apr 2026) |
| Frontiermath tiers 1 3 v2 private | Not checked yet | 36.8% (for 7 Apr 2026) |
| Simpleqa verified | Not checked yet | 34% (for 7 Apr 2026) |
| Apex agents | Not checked yet | 40.9% (for 7 Apr 2026) |
| Chess puzzles | Not checked yet | 20% (for 7 Apr 2026) |
| Exploitbench | Not checked yet | 18.1% (for 7 Apr 2026) |
| Frontiermath 2025 02 28 private | Not checked yet | 33.4% (for 7 Apr 2026) |
| Frontiermath tier 4 2025 07 01 private | Not checked yet | 12.5% (for 7 Apr 2026) |
| Proofbench | Not checked yet | 22.2% (for 7 Apr 2026) |
| Simplebench | Not checked yet | 55.1% (for 7 Apr 2026) |
| Weirdml | Not checked yet | 57.1% (for 7 Apr 2026) |
| Otis mock aime 2024 2025 | Not checked yet | 93.3% (saturated benchmark: the top models all score near the ceiling) (for 7 Apr 2026) |
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.