Compare · ModelsLive · 2 picked · head to head
Gemma 4 31B vs GPT-6 Luna
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
GPT-6 Luna wins on 13/13 benchmarks
GPT-6 Luna wins 13 of 13 shared benchmarks. Leads in speed · knowledge · general.
Category leads
speed·GPT-6 Lunaknowledge·GPT-6 Lunageneral·GPT-6 Lunamath·GPT-6 Luna
Hype vs Reality
Attention vs performance
Gemma 4 31B
#109 by perf·#7 by attention
GPT-6 Luna
#136 by perf·#2 by attention
Best value
Gemma 4 31B
1.1x better value than GPT-6 Luna
Gemma 4 31B
176.7 pts/$
$0.30/M
GPT-6 Luna
166.0 pts/$
$0.30/M
Vendor risk
Who is behind the model
Google DeepMind
$3.53T·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
13 benchmarks · 2 models
Gemma 4 31BGPT-6 Luna
Artificial Analysis · CritPt
GPT-6 Luna leads by +18.0
Gemma 4 31B
1.4
GPT-6 Luna
19.4
Artificial Analysis · GDPval
GPT-6 Luna leads by +40.6
Gemma 4 31B
6.0
GPT-6 Luna
46.6
Artificial Analysis · Humanity's Last Exam
GPT-6 Luna leads by +14.9
Gemma 4 31B
23.6
GPT-6 Luna
38.5
Artificial Analysis · Long Context Reasoning
GPT-6 Luna leads by +13.6
Gemma 4 31B
69.7
GPT-6 Luna
83.3
Artificial Analysis · MMMU Pro
GPT-6 Luna leads by +6.3
Gemma 4 31B
73.4
GPT-6 Luna
79.7
Artificial Analysis · Quality Index
GPT-6 Luna leads by +23.4
Gemma 4 31B
14.7
GPT-6 Luna
38.1
Artificial Analysis · SciCode
GPT-6 Luna leads by +9.1
Gemma 4 31B
45.5
GPT-6 Luna
54.6
Chess Puzzles
GPT-6 Luna leads by +32.6
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
Gemma 4 31B
0.0
GPT-6 Luna
32.7
Dtbench
GPT-6 Luna leads by +12.4
Gemma 4 31B
71.1
GPT-6 Luna
83.5
GPQA diamond
GPT-6 Luna leads by +20.4
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Gemma 4 31B
70.5
GPT-6 Luna
90.9
Lmca
GPT-6 Luna leads by +6.2
Gemma 4 31B
46.2
GPT-6 Luna
52.3
OTIS Mock AIME 2024-2025
GPT-6 Luna leads by +25.6
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Gemma 4 31B
73.3
GPT-6 Luna
98.9
SimpleQA Verified
GPT-6 Luna leads by +31.0
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
Gemma 4 31B
10.4
GPT-6 Luna
41.4
Full benchmark table
| Benchmark | Gemma 4 31B | GPT-6 Luna |
|---|---|---|
Artificial Analysis · CritPt | 1.4 | 19.4 |
Artificial Analysis · GDPval | 6.0 | 46.6 |
Artificial Analysis · Humanity's Last Exam | 23.6 | 38.5 |
Artificial Analysis · Long Context Reasoning | 69.7 | 83.3 |
Artificial Analysis · MMMU Pro | 73.4 | 79.7 |
Artificial Analysis · Quality Index | 14.7 | 38.1 |
Artificial Analysis · SciCode | 45.5 | 54.6 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 0.0 | 32.7 |
Dtbench | 71.1 | 83.5 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 70.5 | 90.9 |
Lmca | 46.2 | 52.3 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 73.3 | 98.9 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 10.4 | 41.4 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.20 | $0.40 | 262K tokens (~131 books) | $2.50 | |
| $0.10 | $0.50 | 1.1M tokens (~525 books) | $2.00 |