# GLM-5 vs Step 3.7 Flash

> Side-by-side benchmark comparison for GLM-5 and Step 3.7 Flash across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/glm-5-vs-step-3-7-flash
- Last updated: October 15, 2026

- Shared sourced benchmarks: 6
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

GLM-5 leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- GLM-5 has the higher overall point estimate 54.8 to 43.7. Conditional score ranges do not establish rank confidence.
- The clearest category separation is in coding, where the averages are 38 for GLM-5 and 30.2 for Step 3.7 Flash.
- The biggest single benchmark swing is BrowseComp in Agentic, with scores of 62% and 75.8%.
- Step 3.7 Flash is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- Step 3.7 Flash also has the larger context window at 256K.

## Model Snapshot

| Property | GLM-5 | Step 3.7 Flash |
|----------|----------|----------|
| Creator | Z.AI | StepFun |
| Type | Open Weight | Open Weight |
| Reasoning | Non-Reasoning | Reasoning |
| Context | 200K | 256K |
| Overall Score | 54.8 | 43.7 |
| Benchmarks Covered | 38 | 11 |
| Pricing (input/output) | $1.00 / $3.20 | $0.20 / $1.15 |

## Category Breakdown

### Agentic

- Winner: Directional only
- GLM-5 public-lane score: 41.7 (Estimated · #62/126)
- Step 3.7 Flash public-lane score: 37.1 (Estimated · #74/126)

| Benchmark | GLM-5 | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 56.2% | Coming soon | Coming soon |
| BrowseComp | 62% | 75.8% | Step 3.7 Flash |
| HLE w/ tools | 50.4% | 47.2% | GLM-5 |
| Claw-Eval | 57.7% | 67.1% | Step 3.7 Flash |
| QwenClawBench | 54.1% | Coming soon | Coming soon |
| τ³-bench results | 65.6% | Coming soon | Coming soon |
| DeepPlanning | 14.6% | Coming soon | Coming soon |
| Toolathlon | 38% | 49.5% | Step 3.7 Flash |
| MCP Atlas | 31.1% | Coming soon | Coming soon |
| MCP-Tasks | 60.8% | Coming soon | Coming soon |
| WideResearch | 69.8% | Coming soon | Coming soon |
| CyberGym | 43.2% | Coming soon | Coming soon |
| Gert Labs | 50.99% | 51.57% | Step 3.7 Flash |
| Terminal-Bench 2.1 | Coming soon | 59.5% | Coming soon |
| DeepSearchQA | Coming soon | 92.8% | Coming soon |

### Coding

- Winner: Directional only
- GLM-5 public-lane score: 38 (Estimated · #69/149)
- Step 3.7 Flash public-lane score: 30.2 (Estimated · #95/149)

| Benchmark | GLM-5 | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 77.8% | Coming soon | Coming soon |
| SWE-bench Verified* | 72.8% | Coming soon | Coming soon |
| SWE-bench Pro | 55.1% | 56.3% | Step 3.7 Flash |
| SWE Multilingual | 73.3% | Coming soon | Coming soon |
| NL2Repo | 35.9% | Coming soon | Coming soon |
| SWE-Rebench | 62.8% | Coming soon | Coming soon |
| React Native Evals | 74.8% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | 56.2% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | Coming soon | 59.5% | Coming soon |

### Reasoning

- Winner: Not comparable
- GLM-5 public-lane score: 70.9 (Unranked · 4 rankable rows)
- Step 3.7 Flash public-lane score: 76.5 (Unranked · 2 rankable rows)

| Benchmark | GLM-5 | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| LongBench v2 | 60.8% | Coming soon | Coming soon |
| AI-Needle | 63.3% | Coming soon | Coming soon |

### Multimodal & Grounded

- Winner: Not comparable
- GLM-5 public-lane score: Coming soon
- Step 3.7 Flash public-lane score: 75.4 (Unranked · 3 rankable rows)

| Benchmark | GLM-5 | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| SimpleVQA | Coming soon | 79.2% | Coming soon |
| V* | Coming soon | 95.3% | Coming soon |

### Knowledge

- Winner: Directional only
- GLM-5 public-lane score: 50.3 (Estimated · #79/182)
- Step 3.7 Flash public-lane score: 45 (Estimated · #96/182)

| Benchmark | GLM-5 | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 86% | Coming soon | Coming soon |
| GPQA-D | 86.0% | Coming soon | Coming soon |
| SuperGPQA | 66.8% | Coming soon | Coming soon |
| MMLU-Pro | 85.7% | Coming soon | Coming soon |
| MMLU-Pro (Arcee) | 85.8% | Coming soon | Coming soon |
| HLE | 30.5% | Coming soon | Coming soon |

### Multilingual

- Winner: Not comparable
- GLM-5 public-lane score: 89.5 (#6/17)
- Step 3.7 Flash public-lane score: Coming soon

| Benchmark | GLM-5 | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| MMLU-ProX | 83.1% | Coming soon | Coming soon |
| NOVA-63 | 55.1% | Coming soon | Coming soon |

### Instruction Following

- Winner: Directional only
- GLM-5 public-lane score: 88.6 (#34/146)
- Step 3.7 Flash public-lane score: 82.1 (#54/146)

| Benchmark | GLM-5 | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| IFEval | 92.6% | Coming soon | Coming soon |

### Mathematics

- Winner: Not comparable
- GLM-5 public-lane score: 83 (Unranked · 6 rankable rows)
- Step 3.7 Flash public-lane score: Coming soon

| Benchmark | GLM-5 | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| AIME26 | 95.8% | Coming soon | Coming soon |
| AIME25 (Arcee) | 93.3% | Coming soon | Coming soon |
| HMMT Feb 2025 | 97.5% | Coming soon | Coming soon |
| HMMT Nov 2025 | 96.9% | Coming soon | Coming soon |
| HMMT Feb 2026 | 86.4% | Coming soon | Coming soon |
| MMAnswerBench | 82.5% | Coming soon | Coming soon |

## FAQ

### Which is better overall, GLM-5 or Step 3.7 Flash?

GLM-5 has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### Where is the biggest gap between GLM-5 and Step 3.7 Flash?

The widest category gap is in coding, where the averages are 38 for GLM-5 and 30.2 for Step 3.7 Flash.

### How many benchmarks does GLM-5 cover on BenchLM?

GLM-5 currently has 38 sourced benchmark scores on BenchLM.

### How many benchmarks does Step 3.7 Flash cover on BenchLM?

Step 3.7 Flash currently has 11 sourced benchmark scores on BenchLM.

## Related Comparisons

- [GLM-5 vs GLM-5.3](/compare/glm-5-vs-glm-5-3)
- [Step 3.7 Flash vs GLM-5.3](/compare/glm-5-3-vs-step-3-7-flash)
- [GLM-5 vs GLM-5.2](/compare/glm-5-vs-glm-5-2)
- [Step 3.7 Flash vs GLM-5.2](/compare/glm-5-2-vs-step-3-7-flash)

## Explore More

- [GLM-5 profile](/models/glm-5)
- [Step 3.7 Flash profile](/models/step-3-7-flash)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)