Compare · ModelsLive · 2 picked · head to head
Claude Sonnet 5 vs GLM 5.3
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Claude Sonnet 5 wins on 7/14 benchmarks
Claude Sonnet 5 wins 7 of 14 shared benchmarks. Leads in general · math.
Category leads
agentic·GLM 5.3knowledge·GLM 5.3coding·GLM 5.3general·Claude Sonnet 5math·Claude Sonnet 5
Hype vs Reality
Attention vs performance
Claude Sonnet 5
#64 by perf·#12 by attention
GLM 5.3
#70 by perf·#5 by attention
Best value
GLM 5.3
2.4x better value than Claude Sonnet 5
Claude Sonnet 5
9.5 pts/$
$6.00/M
GLM 5.3
23.3 pts/$
$2.42/M
Vendor risk
Who is behind the model
Anthropic
$965.0B·Tier 1
z-ai
private · undisclosed
Head to head
14 benchmarks · 2 models
Claude Sonnet 5GLM 5.3
APEX-Agents
GLM 5.3 leads by +2.1
APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments.
Claude Sonnet 5
54.5
GLM 5.3
56.6
Chess Puzzles
Claude Sonnet 5 leads by +8.4
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
Claude Sonnet 5
42.1
GLM 5.3
33.7
Deepswe
GLM 5.3 leads by +15.1
Claude Sonnet 5
53.9
GLM 5.3
69.0
Dtbench
Claude Sonnet 5 leads by +8.0
Claude Sonnet 5
87.5
GLM 5.3
79.5
Frontiercode
Claude Sonnet 5 leads by +2.6
Claude Sonnet 5
42.7
GLM 5.3
40.1
FrontierMath-Tier-4-v2-Private
Claude Sonnet 5
29.3
GLM 5.3
29.3
FrontierMath-Tiers-1-3-v2-Private
GLM 5.3 leads by +3.2
Claude Sonnet 5
65.6
GLM 5.3
68.8
GPQA diamond
GLM 5.3 leads by +0.5
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Claude Sonnet 5
87.4
GLM 5.3
87.9
Lmca
GLM 5.3 leads by +6.5
Claude Sonnet 5
58.9
GLM 5.3
65.3
Mystery Game Puzzles
Claude Sonnet 5 leads by +2.2
Claude Sonnet 5
28.4
GLM 5.3
26.2
OTIS Mock AIME 2024-2025
Claude Sonnet 5 leads by +3.6
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Claude Sonnet 5
94.7
GLM 5.3
91.1
Proofbench
Claude Sonnet 5 leads by +28.0
Claude Sonnet 5
77.0
GLM 5.3
49.0
SimpleQA Verified
GLM 5.3 leads by +7.3
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
Claude Sonnet 5
33.7
GLM 5.3
41.0
WeirdML
GLM 5.3 leads by +6.6
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
Claude Sonnet 5
68.8
GLM 5.3
75.4
Full benchmark table
| Benchmark | Claude Sonnet 5 | GLM 5.3 |
|---|---|---|
APEX-Agents APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments. | 54.5 | 56.6 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 42.1 | 33.7 |
Deepswe | 53.9 | 69.0 |
Dtbench | 87.5 | 79.5 |
Frontiercode | 42.7 | 40.1 |
FrontierMath-Tier-4-v2-Private | 29.3 | 29.3 |
FrontierMath-Tiers-1-3-v2-Private | 65.6 | 68.8 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 87.4 | 87.9 |
Lmca | 58.9 | 65.3 |
Mystery Game Puzzles | 28.4 | 26.2 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 94.7 | 91.1 |
Proofbench | 77.0 | 49.0 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 33.7 | 41.0 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 68.8 | 75.4 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $2.00 | $10.00 | 1.0M tokens (~500 books) | $40.00 | |
| $0.03 | $4.80 | 1.0M tokens (~524 books) | $12.22 |