Model comparison
GLM-5 vs GPT-5.3 Codex
Head-to-head evidence from 17 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: GLM-5 #28 (Supported); GPT-5.3 Codex #26 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. GLM-5 and GPT-5.3 Codex share 17 comparable benchmark results. 2 of 8 categories are comparable. 32 results are unique to GLM-5; 4 to GPT-5.3 Codex.
Updated July 20, 2026- Shared results
- 17
- GLM-5 only
- 32
- GPT-5.3 Codex only
- 4
- Comparable categories
- 2 / 8
Pick GPT-5.3 Codex if you want the stronger benchmark profile. GLM-5 only becomes the better choice if you want the cheaper token bill or you would rather avoid the extra latency and token burn of a reasoning model.
Confidence note. This is a partial-evidence comparison with 17 shared benchmark results across 6 evidence categories; 2 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
GPT-5.3 Codex has the cleaner BenchAlign overall profile here, landing at 66.69 versus 66.06. It is a real lead, but still close enough that category-level strengths matter more than the headline number.
GPT-5.3 Codex's sharpest advantage is in agentic, where it averages 71.4 against 56.2. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 56.2% to 77.3%.
GPT-5.3 Codex is also the more expensive model on tokens at $1.75 input / $14.00 output per 1M tokens, versus $1.00 input / $3.20 output per 1M tokens for GLM-5. That is roughly 4.4x on output cost alone. GPT-5.3 Codex 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. GPT-5.3 Codex gives you the larger context window at 400K, compared with 200K for GLM-5.
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-5 | Δ | GPT-5.3 Codex |
|---|---|---|---|
| Agentic | GLM-556.2 | Margin→ 15.2 | GPT-5.3 Codex71.4 |
| Coding | GLM-566.3 | Margin→ 0.9 | GPT-5.3 Codex67.2 |
| Reasoning | GLM-560.8 | MarginNo overlap | GPT-5.3 CodexNot measured |
| Knowledge | GLM-566.4 | MarginNo overlap | GPT-5.3 CodexNot measured |
| Math | GLM-556.3 | MarginNo overlap | GPT-5.3 CodexNot measured |
| Multilingual | GLM-583.1 | MarginNo overlap | GPT-5.3 CodexNot measured |
| Inst. Following | GLM-592.6 | MarginNo overlap | GPT-5.3 CodexNot measured |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
Terminal-Bench 2.0
AgenticA 56.2%B 77.3%Winner: GPT-5.3 CodexΔ 21.1Terminal-Bench 2.0: GLM-5 scored 56.2%; GPT-5.3 Codex scored 77.3%. GPT-5.3 Codex wins this benchmark. - Source ↗
SWE-bench Verified
CodingA 77.8%B 85%Winner: GPT-5.3 CodexΔ 7.2SWE-bench Verified: GLM-5 scored 77.8%; GPT-5.3 Codex scored 85%. GPT-5.3 Codex wins this benchmark. - Source ↗
SWE-Rebench
CodingA 62.8%B 58.2%Winner: GLM-5Δ 4.6SWE-Rebench: GLM-5 scored 62.8%; GPT-5.3 Codex scored 58.2%. GLM-5 wins this benchmark. - Source ↗
SWE-bench Pro
CodingA 55.1%B 56.8%Winner: GPT-5.3 CodexΔ 1.7SWE-bench Pro: GLM-5 scored 55.1%; GPT-5.3 Codex scored 56.8%. GPT-5.3 Codex wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | GLM-5 | GPT-5.3 Codex | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | GLM-5$1 input / $3.2 output | GPT-5.3 Codex$1.75 input / $14 output | GLM-5 has the lower combined listed price. |
| Generation speedtokens per second | GLM-574 tok/s | GPT-5.3 Codex79 tok/s | GPT-5.3 Codex has the higher measured throughput. |
| First-answer latencyseconds to first token | GLM-51.64 s | GPT-5.3 Codex88.26 s | GLM-5 reaches the first token sooner. |
| Context windowmaximum listed tokens | GLM-5200K | GPT-5.3 Codex400K | GPT-5.3 Codex lists the larger context window. |
Benchmark Deep Dive
AgenticGPT-5.3 Codex wins15 benchmarks
| Benchmark | GLM-5 | GPT-5.3 Codex | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 56.2% | 77.3% | GPT-5.3 Codex leads |
| Claw-EvalSource | 57.7% | — | Not comparable |
| QwenClawBenchSource | 54.1% | — | Not comparable |
| τ³-bench resultsSource | 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 |
| τ²-bench resultsSource | 98.2% | 86% | GLM-5 leads |
| CyberGymSource | 43.2% | — | Not comparable |
| APEX-Agents-AASource | 14.5% | — | Not comparable |
| Gert LabsSource | 50.99% | 57.47% | GPT-5.3 Codex leads |
| OSWorld-VerifiedSource | — | 64.7% | Not comparable |
| JobBenchSource | — | 33.7% | Not comparable |
CodingGPT-5.3 Codex wins8 benchmarks
| Benchmark | GLM-5 | GPT-5.3 Codex | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 77.8% | 85% | GPT-5.3 Codex leads |
| SWE-bench Verified*Source | 72.8% | — | Not comparable |
| SWE-bench ProSource | 55.1% | 56.8% | GPT-5.3 Codex leads |
| SWE MultilingualSource | 73.3% | — | Not comparable |
| SWE-RebenchSource | 62.8% | 58.2% | GLM-5 leads |
| React Native EvalsSource | 74.8% | — | Not comparable |
| AA-SciCodeSource | 46.2% | 53.2% | GPT-5.3 Codex leads |
| Vibe Code BenchSource | — | 61.77% | Not comparable |
Reasoning4 benchmarks
Knowledge12 benchmarks
| Benchmark | GLM-5 | GPT-5.3 Codex | 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% | 44.3% | GPT-5.3 Codex leads |
| AA-GPQA DiamondSource | 82.0% | 91.5% | GPT-5.3 Codex leads |
| AA-HLESource | 27.2% | 39.9% | GPT-5.3 Codex leads |
| AA-Omniscience IndexSource | 2.0% | 9.9% | GPT-5.3 Codex leads |
| AA-Omniscience AccuracySource | 26.9% | 51.8% | GPT-5.3 Codex leads |
| AA-Omniscience Hallucination RateSource | 34.0% | 86.9% | GLM-5 leads |
Math8 benchmarks
| Benchmark | GLM-5 | GPT-5.3 Codex | 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
Multimodal2 benchmarks
Frequently Asked Questions (3)
Which is better, GLM-5 or GPT-5.3 Codex?
GPT-5.3 Codex is ahead on BenchLM's BenchAlign leaderboard, 66.69 to 66.06. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 56.2% and 77.3%.
Which is better for coding, GLM-5 or GPT-5.3 Codex?
GPT-5.3 Codex has the edge for coding in this comparison, averaging 67.2 versus 66.3. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, GLM-5 or GPT-5.3 Codex?
GPT-5.3 Codex has the edge for agentic tasks in this comparison, averaging 71.4 versus 56.2. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Related Comparisons
Explore More
Choose a model with this week’s evidence
Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.
One email each week. Unsubscribe anytime.