Model comparison
GLM-4.7 vs Phi-4
Head-to-head evidence from 11 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: GLM-4.7 #45 (Supported); Phi-4 #202 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. GLM-4.7 and Phi-4 share 11 comparable benchmark results. 0 of 8 categories are comparable. 19 results are unique to GLM-4.7; 0 to Phi-4.
Updated July 24, 2026- Shared results
- 11
- GLM-4.7 only
- 19
- Phi-4 only
- 0
- Comparable categories
- 0 / 8
Benchmark data for GLM-4.7 and Phi-4 is coming soon on BenchLM.
Confidence note. This is a partial-evidence comparison with 11 shared benchmark results across 5 evidence categories; 0 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
BenchLM has partial data for these models, but not enough overlapping benchmark coverage to produce a fair score-level comparison yet.
GLM-4.7 has the larger context window at 200K, compared with 16K for Phi-4.
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 | GLM-4.7 | Δ | Phi-4 |
|---|---|---|---|
| Agentic | GLM-4.745.7 | MarginNo overlap | Phi-4Not measured |
| Coding | GLM-4.775.4 | MarginNo overlap | Phi-4Not measured |
| Knowledge | GLM-4.751.8 | MarginNo overlap | Phi-4Not measured |
| Math | GLM-4.71.8 | MarginNo overlap | Phi-4Not measured |
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | GLM-4.7 | Phi-4 | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | GLM-4.7$0 input / $0 output | Phi-4$0 input / $0 output | Listed prices are equal. |
| Generation speedtokens per second | GLM-4.782 tok/s | Phi-435 tok/s | GLM-4.7 has the higher measured throughput. |
| First-answer latencyseconds to first token | GLM-4.71.10 s | Phi-42.02 s | GLM-4.7 reaches the first token sooner. |
| Context windowmaximum listed tokens | GLM-4.7200K | Phi-416K | GLM-4.7 lists the larger context window. |
Benchmark Deep Dive
Agentic8 benchmarks
| Benchmark | GLM-4.7 | Phi-4 | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 41% | — | Not comparable |
| BrowseCompSource | 52% | — | Not comparable |
| VITA-BenchSource | 15.5% | — | Not comparable |
| AA Agentic IndexSource | 25.4% | — | Not comparable |
| τ²-bench resultsSource | 95.9% | 0% | GLM-4.7 leads |
| Gert LabsSource | 39.95% | — | Not comparable |
| GDPval-AASource | 33.3% | — | Not comparable |
| GDPval-AASource | 1166 | — | Not comparable |
Coding6 benchmarks
Reasoning2 benchmarks
Knowledge9 benchmarks
| Benchmark | GLM-4.7 | Phi-4 | Result |
|---|---|---|---|
| GPQASource | 85.7% | — | Not comparable |
| MMLU-ProSource | 84.3% | — | Not comparable |
| HLESource | 24.8% | — | Not comparable |
| Artificial Analysis Intelligence IndexSource | 33.7% | 4.9% | GLM-4.7 leads |
| AA-GPQA DiamondSource | 85.9% | 57.5% | GLM-4.7 leads |
| AA-HLESource | 25.1% | 4.1% | GLM-4.7 leads |
| AA-Omniscience IndexSource | -34.6% | -56.7% | GLM-4.7 leads |
| AA-Omniscience AccuracySource | 29.3% | 13.2% | GLM-4.7 leads |
| AA-Omniscience Hallucination RateSource | 90.3% | 80.5% | Phi-4 leads |
Math3 benchmarks
Multimodal1 benchmarks
| Benchmark | GLM-4.7 | Phi-4 | Result |
|---|---|---|---|
| Design Arena WebsiteSource | 1255 | — | Not comparable |
Inst. Following1 benchmarks
| Benchmark | GLM-4.7 | Phi-4 | Result |
|---|---|---|---|
| AA-IFBenchSource | 67.9% | 23.5% | GLM-4.7 leads |
Frequently Asked Questions (3)
Can I compare GLM-4.7 and Phi-4 on BenchLM yet?
Not fully yet. BenchLM is tracking both models, but the sourced benchmark breakdown for this comparison is still coming soon.
Why does this comparison show “coming soon”?
BenchLM only shows category winners and benchmark-level calls when we have sourced results that can be compared fairly. For these models, the public benchmark coverage is not complete enough yet.
What data is available for GLM-4.7 and Phi-4 today?
GLM-4.7: $0.00 input / $0.00 output per 1M tokens Phi-4: $0.00 input / $0.00 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.