Compare · ModelsLive · 2 picked · head to head
GPT-5.6 Luna vs Grok 4.3
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
GPT-5.6 Luna wins on 9/10 benchmarks
GPT-5.6 Luna wins 9 of 10 shared benchmarks. Leads in knowledge · general · math.
Category leads
knowledge·GPT-5.6 Lunageneral·GPT-5.6 Lunamath·GPT-5.6 Lunacoding·GPT-5.6 Luna
Hype vs Reality
Attention vs performance
GPT-5.6 Luna
#84 by perf·#9 by attention
Grok 4.3
#76 by perf·#14 by attention
Best value
GPT-5.6 Luna
2.6x better value than Grok 4.3
GPT-5.6 Luna
79.0 pts/$
$0.70/M
Grok 4.3
30.0 pts/$
$1.88/M
Vendor risk
Who is behind the model
OpenAI
$840.0B·Tier 1
xAI
$250.0B·Tier 1
Head to head
10 benchmarks · 2 models
GPT-5.6 LunaGrok 4.3
Chess Puzzles
GPT-5.6 Luna leads by +26.3
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
GPT-5.6 Luna
40.0
Grok 4.3
13.7
Dtbench
Grok 4.3 leads by +2.7
GPT-5.6 Luna
81.8
Grok 4.3
84.5
FrontierMath-Tier-4-v2-Private
GPT-5.6 Luna leads by +46.3
GPT-5.6 Luna
61.0
Grok 4.3
14.6
FrontierMath-Tiers-1-3-v2-Private
GPT-5.6 Luna leads by +41.4
GPT-5.6 Luna
86.4
Grok 4.3
45.1
GPQA diamond
GPT-5.6 Luna leads by +3.8
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
GPT-5.6 Luna
92.5
Grok 4.3
88.7
Lmca
GPT-5.6 Luna leads by +12.0
GPT-5.6 Luna
57.1
Grok 4.3
45.1
OTIS Mock AIME 2024-2025
GPT-5.6 Luna leads by +5.0
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
GPT-5.6 Luna
98.3
Grok 4.3
93.3
Proofbench
GPT-5.6 Luna leads by +49.0
GPT-5.6 Luna
60.0
Grok 4.3
11.0
SimpleQA Verified
GPT-5.6 Luna leads by +7.8
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
GPT-5.6 Luna
41.0
Grok 4.3
33.2
WeirdML
GPT-5.6 Luna leads by +11.0
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
GPT-5.6 Luna
60.9
Grok 4.3
49.9
Full benchmark table
| Benchmark | GPT-5.6 Luna | Grok 4.3 |
|---|---|---|
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 40.0 | 13.7 |
Dtbench | 81.8 | 84.5 |
FrontierMath-Tier-4-v2-Private | 61.0 | 14.6 |
FrontierMath-Tiers-1-3-v2-Private | 86.4 | 45.1 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 92.5 | 88.7 |
Lmca | 57.1 | 45.1 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 98.3 | 93.3 |
Proofbench | 60.0 | 11.0 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 41.0 | 33.2 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 60.9 | 49.9 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.20 | $1.20 | 1.1M tokens (~525 books) | $4.50 | |
| $1.25 | $2.50 | 1.0M tokens (~500 books) | $15.63 |
People also compared