Compare · ModelsLive · 2 picked · head to head
GLM 5.2 vs gpt-oss-120b
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
GLM 5.2 wins on 20/21 benchmarks
GLM 5.2 wins 20 of 21 shared benchmarks. Leads in speed · agentic · arena.
Category leads
speed·GLM 5.2agentic·GLM 5.2arena·GLM 5.2knowledge·GLM 5.2general·GLM 5.2coding·GLM 5.2reasoning·GLM 5.2language·GLM 5.2math·GLM 5.2
Hype vs Reality
Attention vs performance
GLM 5.2
#75 by perf·#3 by attention
gpt-oss-120b
#140 by perf·no signal
Best value
gpt-oss-120b
7.9x better value than GLM 5.2
GLM 5.2
16.5 pts/$
$3.40/M
gpt-oss-120b
131.5 pts/$
$0.38/M
Vendor risk
Who is behind the model
z-ai
private · undisclosed
OpenAI
$840.0B·Tier 1
Head to head
21 benchmarks · 2 models
GLM 5.2gpt-oss-120b
Artificial Analysis · Quality Index
GLM 5.2 leads by +39.5
GLM 5.2
51.1
gpt-oss-120b
11.6
APEX-Agents
GLM 5.2 leads by +40.5
APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments.
GLM 5.2
45.2
gpt-oss-120b
4.7
Chatbot Arena Elo · Overall
GLM 5.2 leads by +119.4
GLM 5.2
1471.0
gpt-oss-120b
1351.6
Chess Puzzles
GLM 5.2 leads by +2.1
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
GLM 5.2
17.9
gpt-oss-120b
15.8
Dtbench
GLM 5.2 leads by +28.9
GLM 5.2
89.3
gpt-oss-120b
60.5
GPQA diamond
GLM 5.2 leads by +25.2
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
GLM 5.2
92.9
gpt-oss-120b
67.7
LiveBench · Agentic Coding
GLM 5.2 leads by +56.7
GLM 5.2
73.3
gpt-oss-120b
16.7
LiveBench · Coding
GLM 5.2 leads by +19.4
GLM 5.2
79.7
gpt-oss-120b
60.2
LiveBench · Data Analysis
GLM 5.2 leads by +34.9
GLM 5.2
73.7
gpt-oss-120b
38.8
LiveBench · If
GLM 5.2 leads by +12.0
GLM 5.2
62.3
gpt-oss-120b
50.3
LiveBench · Language
GLM 5.2 leads by +27.6
GLM 5.2
76.2
gpt-oss-120b
48.6
LiveBench · Mathematics
GLM 5.2 leads by +20.9
GLM 5.2
89.8
gpt-oss-120b
68.9
LiveBench · Overall
GLM 5.2 leads by +30.1
GLM 5.2
76.2
gpt-oss-120b
46.1
LiveBench · Reasoning
GLM 5.2 leads by +39.4
GLM 5.2
78.6
gpt-oss-120b
39.2
Lmca
GLM 5.2 leads by +27.9
GLM 5.2
53.9
gpt-oss-120b
26.1
Mystery Game Puzzles
GLM 5.2 leads by +10.8
GLM 5.2
10.8
gpt-oss-120b
0.0
OTIS Mock AIME 2024-2025
gpt-oss-120b leads by +2.5
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
GLM 5.2
86.4
gpt-oss-120b
88.9
SimpleBench
GLM 5.2 leads by +44.0
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
GLM 5.2
50.6
gpt-oss-120b
6.5
SimpleQA Verified
GLM 5.2 leads by +20.3
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
GLM 5.2
34.2
gpt-oss-120b
13.9
Surface Evolver Bench
GLM 5.2 leads by +30.6
GLM 5.2
55.6
gpt-oss-120b
25.0
WeirdML
GLM 5.2 leads by +22.0
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
GLM 5.2
70.1
gpt-oss-120b
48.2
Full benchmark table
| Benchmark | GLM 5.2 | gpt-oss-120b |
|---|---|---|
Artificial Analysis · Quality Index | 51.1 | 11.6 |
APEX-Agents APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments. | 45.2 | 4.7 |
Chatbot Arena Elo · Overall | 1471.0 | 1351.6 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 17.9 | 15.8 |
Dtbench | 89.3 | 60.5 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 92.9 | 67.7 |
LiveBench · Agentic Coding | 73.3 | 16.7 |
LiveBench · Coding | 79.7 | 60.2 |
LiveBench · Data Analysis | 73.7 | 38.8 |
LiveBench · If | 62.3 | 50.3 |
LiveBench · Language | 76.2 | 48.6 |
LiveBench · Mathematics | 89.8 | 68.9 |
LiveBench · Overall | 76.2 | 46.1 |
LiveBench · Reasoning | 78.6 | 39.2 |
Lmca | 53.9 | 26.1 |
Mystery Game Puzzles | 10.8 | 0.0 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 86.4 | 88.9 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 50.6 | 6.5 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 34.2 | 13.9 |
Surface Evolver Bench | 55.6 | 25.0 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 70.1 | 48.2 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.01 | $6.80 | 1.0M tokens (~524 books) | $17.05 | |
| $0.15 | $0.60 | 131K tokens (~66 books) | $2.62 |