Verdict
GPT-5.5 leads 20–1 across 21 shared benchmarks.
GLM-5.2 1 · GPT-5.5 20 · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Unknown: GPT-5.5 leads 6–0 across 6 shared unknown benchmarks (largest gap: Mystery Game Puzzles, 51.53 vs 10.77 — protocols undisclosed).
Reasoning: GPT-5.5 leads 4–0 across 4 shared reasoning benchmarks (largest gap: SimpleQA Verified, 63 vs 34.2 — protocols undisclosed).
Coding: GPT-5.5 leads 2–0 across 2 shared coding benchmarks (largest gap: DeepSWE, 67.04 vs 43.78 — single evaluator).
Math: GPT-5.5 leads 2–0 across 2 shared math benchmarks (largest gap: FrontierMath-Tier-4-v2-Private, 72.5 vs 29.27 — single evaluator).
Vendor claims — compare against the measured scores above. A claim is what a developer says about its own model, not an independent measurement.
Coding
“Advanced Coding with Flexible Effort: Stronger coding capabilities with multiple thinking effort levels to balance performance and latency”
Context Handling
“We propose IndexShare, which reuses the same indexer across every four sparse attention layers, reducing per-token FLOPs by 2.9x at a 1M context length.”
General
“Pure Open: An MIT open-source license - no regional limits, technical access without borders”
Agentic / Tool Use
“The gains are especially strong in agentic coding, computer use, knowledge work, and early scientific research”
Coding
“It excels at writing and debugging code, researching online, analyzing data, creating documents and spreadsheets, operating software, and moving across tools until a task is finished.”
General
“We're releasing GPT-5.5, our smartest and most intuitive to use model yet, and the next step toward a new way of getting work done on a computer.”
Speed / Latency
“GPT-5.5 matches GPT-5.4 per-token latency in real-world serving, while performing at a much higher level of intelligence.”
GPT-5.5 leads 20–1 across 21 shared benchmarks. GLM-5.2 leads 1 benchmark and GPT-5.5 leads 20. Higher isn't always better — see the integrity caveats on each benchmark.
GLM-5.2 and GPT-5.5 have 21 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.
GPT-5.5 leads unknown 6–0. GPT-5.5 leads reasoning 4–0.