GLM-5
| Released | 2026-02-12 |
|---|---|
| Price per 1M | $0.60 in · $2.69 out |
| Overall score | 52.5 · rank 97 |
| Context window | 204,800 tokens |
| Provider | Zhipu AI |
| Weights | Open weights |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 52.5 | 97 | 24 |
| Overall: Coding | 51.9 | 92 | 16 |
| Overall: Reasoning | 52.1 | 97 | 11 |
| Overall: Agentic work | 52.0 | 101 | 14 |
| Overall: Frontend | 48.8 | 103 | 4 |
| Coding | 53.5 | 91 | 2 |
| Agents | 51.2 | 99 | 6 |
| Reasoning | 52.7 | 93 | 6 |
| Math | 50.9 | 103 | 4 |
| Knowledge | 52.8 | 79 | 1 |
| Frontend | 46.4 | 84 | 2 |
| General | 56.4 | 53 | 3 |
| Value vs price | +4.4 | 81 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 52.3 ±1.9 | 21 |
| Thinking | 52.8 ±3.5 | 6 |
Evidence
Coding 53.5 ±3.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LiveCodeBench (Vals run) | 81.9% | Vals AI | 2026-09-01 |
| SWE-bench Verified (Epoch run) | 72.1% | Epoch AI | 2026-02-15 |
| SWE-bench Verified (Vals run) | 71.4% | Vals AI | 2026-09-01 |
Agents 51.2 ±3.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 2.0 | 52.4% | Epoch AI | 2026-02-11 |
| tau2-bench Banking Knowledge | 9.8% | tau2-bench | 2026-02-27 |
| tau2-bench Airline | 82.5% | tau2-bench | 2026-02-27 |
| Vending-Bench 2 | $4,432 | Epoch AI | 2026-11-11 |
| tau2-bench Telecom | 86.8% | tau2-bench | 2026-02-27 |
| tau2-bench Retail | 73.7% | tau2-bench | 2026-02-27 |
Reasoning 52.7 ±2.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Extended NYT Connections | 74.8% | Lech Mazur | 2026-11-10 |
| ARC-AGI-2 | 4.9% | Epoch AI | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 4.9% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 44.7% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 44.7% | Epoch AI | 2026-11-11 |
| GPQA Diamond | 87.8% | Epoch AI | 2026-02-12 |
| GPQA Diamond (Vals run) | 83.3% | Vals AI | 2026-09-01 |
| Kagi Reasoning Benchmark | 75.0% | Kagi | 2026-11-11 |
| SimpleBench | 53.2% | SimpleBench | 2026-02-17 |
| SimpleBench | 53.2% | Epoch AI | 2026-11-11 |
Math 50.9 ±1.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 (2025 set) | 16.4% | Epoch AI | 2026-02-19 |
| FrontierMath Tier 4 (2025 set) | 2.1% | Epoch AI | 2026-02-19 |
| OTIS Mock AIME 2024-2025 | 80.0% | Epoch AI | 2026-02-12 |
| MathArena Final-Answer Competitions | 65.7% | MathArena | 2026-11-11 |
Knowledge 52.8 ±4.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMLU-Pro (Vals run) | 86.0% | Vals AI | 2026-09-01 |
Frontend 46.4 ±0.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 23.4% | Vals AI | 2026-11-09 |
| LMArena WebDev | 1,435 | LMArena | 2026-11-09 |
General 56.4 ±3.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Text | 1,457 | LMArena | 2026-11-09 |
| EQ-Bench Creative Writing v3 | 1,601 | EQ-Bench | 2026-11-11 |
| EQ-Bench Longform Creative Writing | 70.9% | EQ-Bench | 2026-11-11 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| Kagi Reasoning Benchmark | 51.7% | Kagi | A stronger configuration result was used |
Names matched to this model
glm-5