Model comparison
Composer 2.5 vs GLM-5
Head-to-head evidence from 2 shared benchmark results across 2 categories. Overall scores shown here use BenchLM's provisional ranking lane.
Verified leaderboard positions: Composer 2.5 unranked; GLM-5 #16
Evidence parity. Composer 2.5 and GLM-5 share 2 comparable benchmark results. 1 of 8 categories are comparable. 3 results are unique to Composer 2.5; 48 to GLM-5.
Updated July 14, 2026- Shared results
- 2
- Composer 2.5 only
- 3
- GLM-5 only
- 48
- Comparable categories
- 1 / 8
Pick Composer 2.5 if you want the stronger benchmark profile. GLM-5 only becomes the better choice if you would rather avoid the extra latency and token burn of a reasoning model.
Confidence note. This is a partial-evidence comparison with 2 shared benchmark results across 2 evidence categories; 1 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
Composer 2.5 finishes one point ahead on BenchLM's provisional leaderboard, 64 to 63. That is enough to call, but not enough to treat as a blowout. This matchup comes down to a few meaningful edges rather than one model dominating the board.
Composer 2.5's sharpest advantage is in agentic, where it averages 69.3 against 56.2. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 69.3% to 56.2%.
GLM-5 is also the more expensive model on tokens at $1.00 input / $3.20 output per 1M tokens, versus $0.50 input / $2.50 output per 1M tokens for Composer 2.5. Composer 2.5 is the reasoning model in the pair, while GLM-5 is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
| Category | Composer 2.5 | Δ | GLM-5 |
|---|---|---|---|
| Agentic | Composer 2.569.3 | Margin← 13.1 | GLM-556.2 |
| Coding | Composer 2.5Not measured | MarginNo overlap | GLM-563.3 |
| Reasoning | Composer 2.5Not measured | MarginNo overlap | GLM-560.8 |
| Knowledge | Composer 2.5Not measured | MarginNo overlap | GLM-566.6 |
| Math | Composer 2.5Not measured | MarginNo overlap | GLM-556.3 |
| Multilingual | Composer 2.5Not measured | MarginNo overlap | GLM-583.1 |
| Inst. Following | Composer 2.5Not measured | MarginNo overlap | GLM-592.6 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
Terminal-Bench 2.0
AgenticA 69.3%B 56.2%Winner: Composer 2.5Δ 13.1Terminal-Bench 2.0: Composer 2.5 scored 69.3%; GLM-5 scored 56.2%. Composer 2.5 wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Composer 2.5 | GLM-5 | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Composer 2.5$0.5 input / $2.5 output | GLM-5$1 input / $3.2 output | Composer 2.5 has the lower combined listed price. |
| Generation speedtokens per second | Composer 2.5Not available | GLM-574 tok/s | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Composer 2.5Not available | GLM-51.64 s | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Composer 2.5200K | GLM-5200K | Listed context windows are equal. |
Benchmark Deep Dive
AgenticComposer 2.5 wins13 benchmarks
| Benchmark | Composer 2.5 | GLM-5 | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 69.3% | 56.2% | Composer 2.5 leads |
| Claw-EvalSource | — | 57.7% | Not comparable |
| QwenClawBenchSource | — | 54.1% | Not comparable |
| TAU3-BenchSource | — | 65.6% | Not comparable |
| DeepPlanningSource | — | 14.6% | Not comparable |
| ToolathlonSource | — | 38% | Not comparable |
| MCP AtlasSource | — | 31.1% | Not comparable |
| MCP-TasksSource | — | 60.8% | Not comparable |
| WideResearchSource | — | 69.8% | Not comparable |
| Tau2-TelecomSource | — | 98.2% | Not comparable |
| CyberGymSource | — | 43.2% | Not comparable |
| APEX-Agents-AASource | — | 14.5% | Not comparable |
| Gert LabsSource | — | 50.99% | Not comparable |
Coding11 benchmarks
| Benchmark | Composer 2.5 | GLM-5 | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 69.3% | — | Not comparable |
| SWE MultilingualSource | 79.8% | 73.3% | Composer 2.5 leads |
| cursorBench31Source | 63.2% | — | Not comparable |
| cursorBench32Source | 56.1% | — | Not comparable |
| SWE-bench VerifiedSource | — | 77.8% | Not comparable |
| SWE-bench Verified*Source | — | 72.8% | Not comparable |
| SWE-bench ProSource | — | 55.1% | Not comparable |
| SWE-RebenchSource | — | 62.8% | Not comparable |
| React Native EvalsSource | — | 74.8% | Not comparable |
| Terminal-Bench HardSource | — | 43.2% | Not comparable |
| AA-SciCodeSource | — | 46.2% | Not comparable |
Reasoning4 benchmarks
Knowledge12 benchmarks
| Benchmark | Composer 2.5 | GLM-5 | Result |
|---|---|---|---|
| GPQASource | — | 86% | Not comparable |
| GPQA-DSource | — | 86.0% | Not comparable |
| SuperGPQASource | — | 66.8% | Not comparable |
| MMLU-ProSource | — | 85.7% | Not comparable |
| MMLU-Pro (Arcee)Source | — | 85.8% | Not comparable |
| HLESource | — | 50.4% | Not comparable |
| Artificial Analysis Intelligence IndexSource | — | 39.5% | Not comparable |
| AA-GPQA DiamondSource | — | 82.0% | Not comparable |
| AA-HLESource | — | 27.2% | Not comparable |
| AA-Omniscience IndexSource | — | 2.0% | Not comparable |
| AA-Omniscience AccuracySource | — | 26.9% | Not comparable |
| AA-Omniscience Hallucination RateSource | — | 34.0% | Not comparable |
Math8 benchmarks
| Benchmark | Composer 2.5 | GLM-5 | Result |
|---|---|---|---|
| AIME26Source | — | 95.8% | Not comparable |
| AIME25 (Arcee)Source | — | 93.3% | Not comparable |
| HMMT Feb 2025Source | — | 97.5% | Not comparable |
| HMMT Nov 2025Source | — | 96.9% | Not comparable |
| HMMT Feb 2026Source | — | 86.4% | Not comparable |
| MMAnswerBenchSource | — | 82.5% | Not comparable |
| FrontierMath v2 (Tiers 1-3)Source | — | 16.434% | Not comparable |
| FrontierMath v2 (Tier 4)Source | — | 2.100% | Not comparable |
Multilingual2 benchmarks
Multimodal1 benchmarks
| Benchmark | Composer 2.5 | GLM-5 | Result |
|---|---|---|---|
| Design Arena WebsiteSource | — | 1282 | Not comparable |
Frequently Asked Questions (2)
Which is better, Composer 2.5 or GLM-5?
Composer 2.5 is ahead on BenchLM's provisional leaderboard, 64 to 63. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 69.3% and 56.2%.
Which is better for agentic tasks, Composer 2.5 or GLM-5?
Composer 2.5 has the edge for agentic tasks in this comparison, averaging 69.3 versus 56.2. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Related Comparisons
Explore More
The AI models change fast. We track them for you.
A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.