Compare · ModelsLive · 2 picked · head to head
GLM 5.2 vs GPT-5.6 Luna
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
GPT-5.6 Luna wins on 13/17 benchmarks
GPT-5.6 Luna wins 13 of 17 shared benchmarks. Leads in reasoning · knowledge · coding.
Category leads
reasoning·GPT-5.6 Lunaknowledge·GPT-5.6 Lunacoding·GPT-5.6 Lunageneral·GPT-5.6 Lunamath·GPT-5.6 Luna
Hype vs Reality
Attention vs performance
GLM 5.2
#67 by perf·#3 by attention
GPT-5.6 Luna
#59 by perf·#4 by attention
Best value
GPT-5.6 Luna
3.7x better value than GLM 5.2
GLM 5.2
22.6 pts/$
$2.50/M
GPT-5.6 Luna
82.4 pts/$
$0.70/M
Vendor risk
Who is behind the model
z-ai
private · undisclosed
OpenAI
$840.0B·Tier 1
Head to head
17 benchmarks · 2 models
GLM 5.2GPT-5.6 Luna
ARC-AGI
GPT-5.6 Luna leads by +11.0
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
GLM 5.2
77.0
GPT-5.6 Luna
88.0
ARC-AGI-2
GPT-5.6 Luna leads by +36.8
ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data.
GLM 5.2
22.8
GPT-5.6 Luna
59.5
Chess Puzzles
GPT-5.6 Luna leads by +20.0
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
GLM 5.2
16.9
GPT-5.6 Luna
36.9
Deepswe
GPT-5.6 Luna leads by +23.4
GLM 5.2
43.8
GPT-5.6 Luna
67.2
Dtbench
GLM 5.2 leads by +7.5
GLM 5.2
89.3
GPT-5.6 Luna
81.8
Frontiercode
GPT-5.6 Luna leads by +15.3
GLM 5.2
24.5
GPT-5.6 Luna
39.8
FrontierMath-Tier-4-v2-Private
GPT-5.6 Luna leads by +31.7
GLM 5.2
29.3
GPT-5.6 Luna
61.0
FrontierMath-Tiers-1-3-v2-Private
GPT-5.6 Luna leads by +22.9
GLM 5.2
59.2
GPT-5.6 Luna
82.1
GPQA diamond
GLM 5.2 leads by +0.3
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
89.1
GPT-5.6 Luna
88.8
Lmca
GPT-5.6 Luna leads by +3.2
GLM 5.2
53.9
GPT-5.6 Luna
57.1
Mystery Game Puzzles
GPT-5.6 Luna leads by +2.2
GLM 5.2
10.8
GPT-5.6 Luna
13.0
OTIS Mock AIME 2024-2025
GPT-5.6 Luna leads by +12.0
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
GLM 5.2
86.4
GPT-5.6 Luna
98.3
Proofbench
GPT-5.6 Luna leads by +25.0
GLM 5.2
35.0
GPT-5.6 Luna
60.0
SimpleBench
GLM 5.2 leads by +14.4
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
GLM 5.2
50.6
GPT-5.6 Luna
36.2
SimpleQA Verified
GPT-5.6 Luna leads by +6.8
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-5.6 Luna
41.0
Surface Evolver Bench
GPT-5.6 Luna leads by +6.3
GLM 5.2
55.6
GPT-5.6 Luna
61.9
WeirdML
GLM 5.2 leads by +9.3
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
GLM 5.2
70.1
GPT-5.6 Luna
60.9
Full benchmark table
| Benchmark | GLM 5.2 | GPT-5.6 Luna |
|---|---|---|
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization. | 77.0 | 88.0 |
ARC-AGI-2 ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data. | 22.8 | 59.5 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 16.9 | 36.9 |
Deepswe | 43.8 | 67.2 |
Dtbench | 89.3 | 81.8 |
Frontiercode | 24.5 | 39.8 |
FrontierMath-Tier-4-v2-Private | 29.3 | 61.0 |
FrontierMath-Tiers-1-3-v2-Private | 59.2 | 82.1 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 89.1 | 88.8 |
Lmca | 53.9 | 57.1 |
Mystery Game Puzzles | 10.8 | 13.0 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 86.4 | 98.3 |
Proofbench | 35.0 | 60.0 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 50.6 | 36.2 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 34.2 | 41.0 |
Surface Evolver Bench | 55.6 | 61.9 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 70.1 | 60.9 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $1.00 | $4.00 | 1.0M tokens (~524 books) | $17.50 | |
| $0.20 | $1.20 | 1.1M tokens (~525 books) | $4.50 |