Model comparison
Command R+ vs GLM-5
GLM-5 is the stronger model overall, scoring 45.9 to 32.0 on the Noometry Index.
Last verified . 20 shared benchmarks.
CohereSummary
- They share 20 benchmarks with published results for both. Command R+ scores higher in 0 categories and GLM-5 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-5 leads 66.2 to 43.7.
- The biggest single-benchmark swing is SimpleBench: 17.4% for Command R+ and 53.2% for GLM-5.
- GLM-5 is cheaper at $1 / $3.20 per million input/output tokens, against $2.50 / $10 for Command R+.
- GLM-5 accepts more context: 205K tokens versus 128K.
Side by side
| Command R+ | GLM-5 | |
|---|---|---|
| Provider | Cohere | Z.ai (Zhipu) |
| Noometry Index | 32.0 | 45.9 |
| Released | 2024-08-30 | 2026-02-11 |
| Weights | Open | Open |
| Context window | 128K | 205K |
| Max output | 4K | 131K |
| Input $ / M tokens | $2.50 | $1 |
| Output $ / M tokens | $10 | $3.20 |
| Results tracked | 34 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
Command R+: 28.6 (#304), GLM-5: 49.0 (#47)
| Benchmark | Command R+ | GLM-5 |
|---|---|---|
| LMArena Coding | 1187 | 1461 |
| SWE-bench Verified | — | 72.1% |
| SWE-bench Verified (bash only) | — | 72.8% |
| LMArena WebDev | — | 1434 |
| SWE-bench Multilingual | — | 69.7% |
| WeirdML | — | 48.2% |
| BigCodeBench Instruct | 33.8% | — |
| LiveBench Coding | 19.1% | — |
| BigCodeBench Complete | 41.9% | — |
| ALE-Bench | — | 765.62 |
| HumanEval+ | 56.7% | — |
| MBPP+ | 63.5% | — |
Agentic & Tool Use Not comparable
Command R+: —, GLM-5: 30.9 (#65)
| Benchmark | Command R+ | GLM-5 |
|---|---|---|
| Terminal-Bench | — | 52.4% |
| τ²-bench Airline | — | 82.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 73.7% |
| τ²-bench Telecom | — | 86.8% |
| Vending-Bench 2 | — | 4,432 |
Reasoning GLM-5 leads
Command R+: 8.9 (#341), GLM-5: 27.6 (#100)
| Benchmark | Command R+ | GLM-5 |
|---|---|---|
| SimpleBench | 17.4% | 53.2% |
| LMArena Hard Prompts | 1186 | 1451 |
| Epoch Capabilities Index | 119.28 | 145.84 |
| ARC-AGI-2 | — | 4.9% |
| Kagi LLM Benchmark | — | 75% |
| NYT Connections (extended) | — | 74.8% |
| ARC-AGI-1 | — | 44.7% |
| Chess Puzzles | — | 10% |
| LiveBench Reasoning | 24.8% | — |
| DTBench | 54.9% | — |
| LiveBench Data Analysis | 38.1% | — |
| LMCA | 5% | — |
| ForecastBench | — | 61 |
| LiveBench | 31.8% | — |
Math GLM-5 leads
Command R+: 26.6 (#239), GLM-5: 44.8 (#66)
| Benchmark | Command R+ | GLM-5 |
|---|---|---|
| LMArena Math | 1188 | 1440 |
| MathArena Final-Answer Competitions | — | 65.7% |
| OTIS Mock AIME 2024-2025 | — | 80% |
| LiveBench Math | 21.3% | — |
| FrontierMath (Feb 2025 set) | — | 16.4% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge GLM-5 leads
Command R+: 35.9 (#165), GLM-5: 52.2 (#59)
| Benchmark | Command R+ | GLM-5 |
|---|---|---|
| Vectara Hallucination Rate | 6.9% | 10.1% |
| LMArena Expert | 1174 | 1454 |
| GPQA Diamond | — | 87.8% |
| MMLU | 69.4% | — |
Multilingual GLM-5 leads
Command R+: 38.8 (#222), GLM-5: 53.9 (#57)
| Benchmark | Command R+ | GLM-5 |
|---|---|---|
| LMArena Non-English | 1216 | 1430 |
| LMArena Chinese | 1226 | 1511 |
| LMArena French | 1208 | 1455 |
| LMArena German | 1216 | 1445 |
| LMArena Japanese | 1166 | 1416 |
| LMArena Korean | 1138 | 1421 |
| LMArena Russian | 1227 | 1436 |
| LMArena Spanish | 1189 | 1452 |
Instruction Following GLM-5 leads
Command R+: 60.2 (#249), GLM-5: 75.4 (#64)
| Benchmark | Command R+ | GLM-5 |
|---|---|---|
| LMArena Instruction Following | 1197 | 1427 |
| LiveBench Instruction Following | 57.6% | — |
Long Context GLM-5 leads
Command R+: 37.3 (#214), GLM-5: 44.6 (#58)
| Benchmark | Command R+ | GLM-5 |
|---|---|---|
| LMArena Longer Query | 1231 | 1446 |
| CL-bench | — | 18.7% |
Writing & Preference GLM-5 leads
Command R+: 43.7 (#223), GLM-5: 66.2 (#38)
| Benchmark | Command R+ | GLM-5 |
|---|---|---|
| LMArena Text | 1229 | 1446 |
| LMArena Creative Writing | 1235 | 1438 |
| LMArena Multi-Turn | 1213 | 1456 |
| EQ-Bench Creative Writing | — | 1601 |
| LiveBench Language | 29.7% | — |
Frequently asked questions
Is Command R+ better than GLM-5?
GLM-5 is the stronger model overall, scoring 45.9 to 32.0 on the Noometry Index.
Which is cheaper, Command R+ or GLM-5?
GLM-5 is cheaper. It lists at $1 per million input tokens and $3.20 per million output tokens; Command R+ lists at $2.50 and $10.
Is Command R+ or GLM-5 better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 28.6 in the Noometry coding category.
Which has the bigger context window?
GLM-5 does, with 205K tokens against 128K.
How many benchmarks do Command R+ and GLM-5 share?
20 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and GLM-5 has 45.