# GLM-5.3 vs Mercury 2.5

> Side-by-side benchmark comparison for GLM-5.3 and Mercury 2.5 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/glm-5-3-vs-mercury-2-5
- Last updated: September 8, 2026

- Shared sourced benchmarks: 0
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

No benchmark verdict yet: there is no shared sourced benchmark row for GLM-5.3 and Mercury 2.5.

## Summary

- GLM-5.3 and Mercury 2.5 do not currently share a sourced benchmark row. The mirror therefore compares metadata, pricing, context windows, and each model's separately reported coverage without naming a benchmark winner.

## Model Snapshot

| Property | GLM-5.3 | Mercury 2.5 |
|----------|----------|----------|
| Creator | Z.AI | Inception |
| Type | Open Weight | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 1M | 260K |
| Independent public score (not head-to-head) | 68.34 | null |
| Benchmarks Covered | 24 | 5 |
| Pricing (input/output) | $0.00 / $0.00 | $0.04 / $0.15 |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- GLM-5.3 public-lane score: 68.4 (Supported · #8/152)
- Mercury 2.5 public-lane score: 44.5 (Estimated · #91/152)

| Benchmark | GLM-5.3 | Mercury 2.5 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.1 | 88.2% | Coming soon | Coming soon |
| terminalBench3 | 28.3% | Coming soon | Coming soon |
| CyberGym | 84.5% | Coming soon | Coming soon |
| ExploitGym | 15.0% | Coming soon | Coming soon |
| Toolathlon-Verified | 73.0% | Coming soon | Coming soon |
| AutomationBench | 48.2% | Coming soon | Coming soon |
| Agents' Last Exam | 28.5% | Coming soon | Coming soon |
| HLE w/ tools | 62.5% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 71.5% | Coming soon | Coming soon |
| τ³-bench results | Coming soon | 96.0% | Coming soon |
| DeepSearchQA | Coming soon | 34.0% | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- GLM-5.3 public-lane score: 61.5 (Supported · #18/151)
- Mercury 2.5 public-lane score: 47.8 (Estimated · #73/151)

| Benchmark | GLM-5.3 | Mercury 2.5 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.1 | 88.2% | Coming soon | Coming soon |
| terminalBench3 | 28.3% | Coming soon | Coming soon |
| deepSwe | 66.9% | Coming soon | Coming soon |
| NL2Repo | 58% | Coming soon | Coming soon |
| ProgramBench | 19.0% | Coming soon | Coming soon |
| FrontierSWE | 78.1% | Coming soon | Coming soon |
| sweMarathon | 42.5% | Coming soon | Coming soon |
| PostTrain Bench | 39.8% | Coming soon | Coming soon |
| VulcanBench v3 | 78.3% | Coming soon | Coming soon |
| OpenHarmony Bench | 60.8% | Coming soon | Coming soon |
| FrontierSWE v2 | 30.2% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 80.5% | Coming soon | Coming soon |
| SWE-bench (Vals) | 95.4% | Coming soon | Coming soon |
| SciCode | Coming soon | 38% | Coming soon |

### Reasoning

- Winner: Insufficient shared evidence
- GLM-5.3 public-lane score: 75.8 (#8/18)
- Mercury 2.5 public-lane score: 67.7 (Unranked · 1 rankable row)

### Knowledge

- Winner: Insufficient shared evidence
- GLM-5.3 public-lane score: 61.9 (Supported · #28/182)
- Mercury 2.5 public-lane score: 48.3 (Estimated · #94/182)

| Benchmark | GLM-5.3 | Mercury 2.5 | Winner |
|-----------|-----------|-----------|--------|
| GPQA Diamond (Vals) | 88.1% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 86.8% | Coming soon | Coming soon |
| GPQA-D | Coming soon | 79.0% | Coming soon |

### Instruction Following

- Winner: Insufficient shared evidence
- GLM-5.3 public-lane score: Coming soon
- Mercury 2.5 public-lane score: 80.1 (#53/121)

| Benchmark | GLM-5.3 | Mercury 2.5 | Winner |
|-----------|-----------|-----------|--------|
| IFBench | Coming soon | 77% | Coming soon |

## FAQ

### Can I compare GLM-5.3 and Mercury 2.5 on BenchLM yet?

Not fully yet. BenchLM is tracking both models, but sourced benchmark coverage is still incomplete for a fair score-level comparison.

### Why does this page show "coming soon" values?

BenchLM only calls winners when public benchmark coverage is available on both sides of the comparison.

## Related Comparisons

- [GLM-5.3 vs GLM-5.2](/compare/glm-5-2-vs-glm-5-3)
- [Mercury 2.5 vs GLM-5.2](/compare/glm-5-2-vs-mercury-2-5)
- [GLM-5.3 vs GLM-5.3-Flash](/compare/glm-5-3-vs-glm-5-3-flash)
- [Mercury 2.5 vs GLM-5.3-Flash](/compare/glm-5-3-flash-vs-mercury-2-5)

## Explore More

- [GLM-5.3 profile](/models/glm-5-3)
- [Mercury 2.5 profile](/models/mercury-2-5)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)