Models / GPT-6 Luna

OpenAI

GPT-6 Luna

93 published results from 8 sources. Each card shows where the number comes from and what it does not measure. The overall leaderboard combines them; here each stands alone.

Provider
OpenAI
Sources
8
Our benchmarks
3
Price per million tokens
$0.10 in · $0.50 out
OpenRouter list price, 1 Oct 2026 · 1,050,000-token context

Measured by Spring Prompt

Measured by Spring Prompt · BulletBench
$0.0072
Cost per game · rank 1 of 10
Unit
US dollars, lower is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
29 Sep 2026
Not shown
Not your cost: prices are those charged on the run date.
Measured by Spring Prompt · BulletBench
50.0%
Games lost on time · rank 8 of 10
Unit
% of games, lower is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
29 Sep 2026
Not shown
Not a business skill: chess against an engine on a real clock, used here as a speed-under-pressure signal.
Measured by Spring Prompt · BulletBench
0.0%
Invalid moves · rank 1 of 10
Unit
% of moves, lower is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
29 Sep 2026
Not shown
Not a business skill: chess against an engine on a real clock, used here as a speed-under-pressure signal.
Measured by Spring Prompt · BulletBench
557
Ladder Elo · rank 2 of 10
Unit
ladder Elo, higher is better
Range
370 to 727
Sample
8 games
Configuration
GPT-6 Luna, provider default reasoning
Measured
29 Sep 2026
Not shown
Not a business skill: chess against an engine on a real clock, used here as a speed-under-pressure signal.
Measured by Spring Prompt · BulletBench
7.0 s
Median move time · rank 8 of 10
Unit
milliseconds, lower is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
29 Sep 2026
Not shown
Not general response speed: replies are one short move.
Measured by Spring Prompt · BulletBench
$0.0016
Cost per game · rank 2 of 24
Unit
US dollars, lower is better
Configuration
GPT-6 Luna (no reasoning), none reasoning
Measured
1 Oct 2026
Not shown
Not your cost: prices are those charged on the run date.
Measured by Spring Prompt · BulletBench
50.0%
Games lost on time · rank 12 of 24
Unit
% of games, lower is better
Configuration
GPT-6 Luna (no reasoning), none reasoning
Measured
1 Oct 2026
Not shown
Not a business skill: chess against an engine on a real clock, used here as a speed-under-pressure signal.
Measured by Spring Prompt · BulletBench
0.0%
Invalid moves · rank 1 of 24
Unit
% of moves, lower is better
Configuration
GPT-6 Luna (no reasoning), none reasoning
Measured
1 Oct 2026
Not shown
Not a business skill: chess against an engine on a real clock, used here as a speed-under-pressure signal.
Measured by Spring Prompt · BulletBench
249
Ladder Elo · rank 5 of 24
Unit
ladder Elo, higher is better
Range
0 to 453
Sample
12 games
Configuration
GPT-6 Luna (no reasoning), none reasoning
Measured
1 Oct 2026
Not shown
Not a business skill: chess against an engine on a real clock, used here as a speed-under-pressure signal.
Measured by Spring Prompt · BulletBench
1.5 s
Median move time · rank 13 of 24
Unit
milliseconds, lower is better
Configuration
GPT-6 Luna (no reasoning), none reasoning
Measured
1 Oct 2026
Not shown
Not general response speed: replies are one short move.
Measured by Spring Prompt · CatalogBench
0.0%
Channel rules broken · rank 1 of 18
Unit
% of products, lower is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
30 Sep 2026
Not shown
Not your catalogue: invented products with generated images, so a model's result on your own feed can differ.
Measured by Spring Prompt · CatalogBench
0.0%
Claims to check · rank 1 of 18
Unit
% of products, lower is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
30 Sep 2026
Not shown
Not your catalogue: invented products with generated images, so a model's result on your own feed can differ.
Measured by Spring Prompt · CatalogBench
97.4%
Content quality · rank 8 of 18
Unit
% of checks, higher is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
30 Sep 2026
Not shown
Not your catalogue: invented products with generated images, so a model's result on your own feed can differ.
Measured by Spring Prompt · CatalogBench
0.0%
Failed outputs · rank 1 of 18
Unit
% of products, lower is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
30 Sep 2026
Not shown
Not a provider outage: provider errors are retried before a product counts as failed.
Measured by Spring Prompt · CatalogBench
0.0%
Missing UK information · rank 1 of 18
Unit
% of products, lower is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
30 Sep 2026
Not shown
Not your catalogue: invented products with generated images, so a model's result on your own feed can differ.
Measured by Spring Prompt · CatalogBench
10.1%
Not findable · rank 16 of 18
Unit
% of products, lower is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
30 Sep 2026
Not shown
Not your catalogue: invented products with generated images, so a model's result on your own feed can differ.
Measured by Spring Prompt · CatalogBench
67.9%
Publish-ready listings · rank 4 of 18
Unit
% of products, higher is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
30 Sep 2026
Not shown
Not your catalogue: invented products with generated images, so a model's result on your own feed can differ.
Measured by Spring Prompt · CatalogBench
51.8%
Reliably publish-ready · rank 4 of 18
Unit
% of products, higher is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
30 Sep 2026
Not shown
Not your catalogue: invented products with generated images, so a model's result on your own feed can differ.
Measured by Spring Prompt · CatalogBench
8.3%
Unsupported claims · rank 4 of 18
Unit
% of products, lower is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
30 Sep 2026
Not shown
Not your catalogue: invented products with generated images, so a model's result on your own feed can differ.
Measured by Spring Prompt · CatalogBench
0.34
Unsupported claims · rank 4 of 18
Unit
claims per product, lower is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
30 Sep 2026
Not shown
Not your catalogue: invented products with generated images, so a model's result on your own feed can differ.
Measured by Spring Prompt · CatalogBench
19.1%
Wrong attributes · rank 9 of 18
Unit
% of products, lower is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
30 Sep 2026
Not shown
Not your catalogue: invented products with generated images, so a model's result on your own feed can differ.
Measured by Spring Prompt · CatalogBench
0.0%
Wrong category or variant · rank 1 of 18
Unit
% of products, lower is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
30 Sep 2026
Not shown
Not your catalogue: invented products with generated images, so a model's result on your own feed can differ.
Measured by Spring Prompt · CatalogBench
100.0%
Channel compliance · rank 1 of 18
Unit
% of products, higher is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
30 Sep 2026
Not shown
Not your catalogue: invented products with generated images, so a model's result on your own feed can differ.
Measured by Spring Prompt · CatalogBench
0.0%
Channel rules broken · rank 1 of 18
Unit
% of products, lower is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
30 Sep 2026
Not shown
Not your catalogue: invented products with generated images, so a model's result on your own feed can differ.
Measured by Spring Prompt · CatalogBench
0.0%
Claims to check · rank 1 of 18
Unit
% of products, lower is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
30 Sep 2026
Not shown
Not your catalogue: invented products with generated images, so a model's result on your own feed can differ.
Measured by Spring Prompt · CatalogBench
100.0%
Conflicts caught · rank 1 of 18
Unit
% of conflicts, higher is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
30 Sep 2026
Not shown
Not your catalogue: invented products with generated images, so a model's result on your own feed can differ.
Measured by Spring Prompt · CatalogBench
97.0%
Content quality · rank 9 of 18
Unit
% of checks, higher is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
30 Sep 2026
Not shown
Not your catalogue: invented products with generated images, so a model's result on your own feed can differ.
Measured by Spring Prompt · CatalogBench
$0.0005
Cost per product · rank 1 of 18
Unit
US dollars, lower is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
30 Sep 2026
Not shown
Not your cost: prices are those charged through OpenRouter on the run date.
Measured by Spring Prompt · CatalogBench
97.0%
Decision accuracy · rank 7 of 18
Unit
% of decisions, higher is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
30 Sep 2026
Not shown
Not your catalogue: invented products with generated images, so a model's result on your own feed can differ.
Measured by Spring Prompt · CatalogBench
0.0%
Failed outputs · rank 1 of 18
Unit
% of products, lower is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
30 Sep 2026
Not shown
Not a provider outage: provider errors are retried before a product counts as failed.
Measured by Spring Prompt · CatalogBench
93.7%
Field accuracy · rank 7 of 18
Unit
% of missing fields, higher is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
30 Sep 2026
Not shown
Not your catalogue: invented products with generated images, so a model's result on your own feed can differ.
Measured by Spring Prompt · CatalogBench
1.7%
Invented values · rank 11 of 18
Unit
% of filled values, lower is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
30 Sep 2026
Not shown
Not your catalogue: invented products with generated images, so a model's result on your own feed can differ.
Measured by Spring Prompt · CatalogBench
0.0%
Missing UK information · rank 1 of 18
Unit
% of products, lower is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
30 Sep 2026
Not shown
Not your catalogue: invented products with generated images, so a model's result on your own feed can differ.
Measured by Spring Prompt · CatalogBench
10.1%
Not findable · rank 16 of 18
Unit
% of products, lower is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
30 Sep 2026
Not shown
Not your catalogue: invented products with generated images, so a model's result on your own feed can differ.
Measured by Spring Prompt · CatalogBench
67.9%
Publish-ready listings · rank 6 of 18
Unit
% of products, higher is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
30 Sep 2026
Not shown
Not your catalogue: invented products with generated images, so a model's result on your own feed can differ.
Measured by Spring Prompt · CatalogBench
55.4%
Reliably publish-ready · rank 5 of 18
Unit
% of products, higher is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
30 Sep 2026
Not shown
Not your catalogue: invented products with generated images, so a model's result on your own feed can differ.
Measured by Spring Prompt · CatalogBench
8.9%
Unsupported claims · rank 4 of 18
Unit
% of products, lower is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
30 Sep 2026
Not shown
Not your catalogue: invented products with generated images, so a model's result on your own feed can differ.
Measured by Spring Prompt · CatalogBench
0.31
Unsupported claims · rank 4 of 18
Unit
claims per product, lower is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
30 Sep 2026
Not shown
Not your catalogue: invented products with generated images, so a model's result on your own feed can differ.
Measured by Spring Prompt · CatalogBench
18.4%
Wrong attributes · rank 11 of 18
Unit
% of products, lower is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
30 Sep 2026
Not shown
Not your catalogue: invented products with generated images, so a model's result on your own feed can differ.
Measured by Spring Prompt · CatalogBench
1.8%
Wrong category or variant · rank 2 of 18
Unit
% of products, lower is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
30 Sep 2026
Not shown
Not your catalogue: invented products with generated images, so a model's result on your own feed can differ.
Measured by Spring Prompt · ROASBench
68.2
Audience score · rank 3 of 17
Unit
score out of 100, higher is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
29 Sep 2026
Not shown
Not real ad performance: the market is a deterministic simulation of one invented skincare brand.
Measured by Spring Prompt · ROASBench
54.8
Business score · rank 3 of 17
Unit
score out of 100, higher is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
29 Sep 2026
Not shown
Not real ad performance: the market is a deterministic simulation of one invented skincare brand.
Measured by Spring Prompt · ROASBench
35.8
Consistency score · rank 4 of 17
Unit
score out of 100, higher is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
29 Sep 2026
Not shown
Not real ad performance: the market is a deterministic simulation of one invented skincare brand.
Measured by Spring Prompt · ROASBench
$738,878
Contribution profit · rank 4 of 17
Unit
simulated US dollars, higher is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
29 Sep 2026
Not shown
Not real ad performance: the market is a deterministic simulation of one invented skincare brand.
Measured by Spring Prompt · ROASBench
$0.0142
Cost of a run · rank 1 of 17
Unit
US dollars, lower is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
29 Sep 2026
Not shown
Not your cost: prices are those charged through OpenRouter on the run date.
Measured by Spring Prompt · ROASBench
0
Months over budget · rank 1 of 17
Unit
months of 12, lower is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
29 Sep 2026
Not shown
Not real ad performance: the market is a deterministic simulation of one invented skincare brand.
Measured by Spring Prompt · ROASBench
53.4
Overall score · rank 3 of 17
Unit
score out of 100, higher is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
29 Sep 2026
Not shown
Not real ad performance: the market is a deterministic simulation of one invented skincare brand.
Measured by Spring Prompt · ROASBench
54.8
Planning score · rank 9 of 17
Unit
score out of 100, higher is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
29 Sep 2026
Not shown
Not real ad performance: the market is a deterministic simulation of one invented skincare brand.
Measured by Spring Prompt · ROASBench
$0.66
Return on ad spend · rank 4 of 17
Unit
profit per $1 spent, higher is better
Configuration
GPT-6 Luna, provider default reasoning
Measured
29 Sep 2026
Not shown
Not real ad performance: the market is a deterministic simulation of one invented skincare brand.

Reported by others

Reported by APEX-Agents
44.3%
Tasks passed · rank 29 of 39
Unit
% of tasks, higher is better
Configuration
GPT-6 Luna (max)
Measured
1 Oct 2026
Not shown
Not your firm's documents or tools; graded by rubric, not by a client.
Reported by Arena (formerly LMArena)
0.05
Confirmed task success · rank 5 of 46
Unit
IPS effect estimate, higher is better
Range
0.01 to 0.08
Sample
3913 observations
Configuration
GPT-6 Luna
Measured
28 Sep 2026
Not shown
Not a success rate: the estimated effect of choosing this model as the agent's orchestrator, against an even mix of the models tested, inside Arena's own harness.
Reported by Arena (formerly LMArena)
-0.03
Praise over complaint · rank 15 of 46
Unit
IPS effect estimate, higher is better
Range
-0.09 to 0.03
Sample
1083 observations
Configuration
GPT-6 Luna
Measured
28 Sep 2026
Not shown
Not a success rate: the estimated effect of choosing this model as the agent's orchestrator, against an even mix of the models tested, inside Arena's own harness.
Reported by Arena (formerly LMArena)
0.02
Steerability · rank 6 of 46
Unit
IPS effect estimate, higher is better
Range
-0.02 to 0.06
Sample
3522 observations
Configuration
GPT-6 Luna
Measured
28 Sep 2026
Not shown
Not a success rate: the estimated effect of choosing this model as the agent's orchestrator, against an even mix of the models tested, inside Arena's own harness.
Reported by Arena (formerly LMArena)
0.00
Tool grounding · rank 1 of 46
Unit
IPS effect estimate, higher is better
Range
0.00 to 0.00
Sample
802714 observations
Configuration
GPT-6 Luna
Measured
28 Sep 2026
Not shown
Not a success rate: the estimated effect of choosing this model as the agent's orchestrator, against an even mix of the models tested, inside Arena's own harness.
Reported by Arena (formerly LMArena)
1,422
Overall · rank 103 of 177
Unit
Arena rating, higher is better
Range
1,414 to 1,430
Sample
4360 votes
Configuration
GPT-6 Luna (max)
Measured
25 Sep 2026
Not shown
Not an error rate: claims that cannot be checked on the web are skipped, and preference still carries most of the weight.
Reported by Arena (formerly LMArena)
1,452
Business, management and finance · rank 22 of 402
Unit
Arena rating, higher is better
Range
1,432 to 1,473
Sample
875 votes
Configuration
GPT-6 Luna (max)
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Arena (formerly LMArena)
1,403
Creative writing · rank 68 of 407
Unit
Arena rating, higher is better
Range
1,382 to 1,423
Sample
939 votes
Configuration
GPT-6 Luna (max)
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Arena (formerly LMArena)
1,505
Expert prompts · rank 4 of 359
Unit
Arena rating, higher is better
Range
1,480 to 1,529
Sample
578 votes
Configuration
GPT-6 Luna (max)
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Arena (formerly LMArena)
1,443
Instruction following · rank 40 of 409
Unit
Arena rating, higher is better
Range
1,429 to 1,457
Sample
1706 votes
Configuration
GPT-6 Luna (max)
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Arena (formerly LMArena)
1,442
Overall · rank 67 of 409
Unit
Arena rating, higher is better
Range
1,434 to 1,451
Sample
4792 votes
Configuration
GPT-6 Luna (max)
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Arena (formerly LMArena)
1,415
Writing, literature and language · rank 67 of 408
Unit
Arena rating, higher is better
Range
1,398 to 1,433
Sample
1245 votes
Configuration
GPT-6 Luna (max)
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Artificial Analysis
32.9
Artificial Analysis Intelligence Index · rank 90 of 314
Unit
index score, higher is better
Configuration
GPT-6 Luna (high)
Measured
1 Oct 2026
Not shown
Not business work, and a blend: read the parts for any one task.
Reported by Artificial Analysis
21.5
Artificial Analysis Intelligence Index · rank 166 of 314
Unit
index score, higher is better
Configuration
GPT-6 Luna (low)
Measured
1 Oct 2026
Not shown
Not business work, and a blend: read the parts for any one task.
Reported by Artificial Analysis
38.1
Artificial Analysis Intelligence Index · rank 67 of 314
Unit
index score, higher is better
Configuration
GPT-6 Luna (max)
Measured
1 Oct 2026
Not shown
Not business work, and a blend: read the parts for any one task.
Reported by Artificial Analysis
29.9
Artificial Analysis Intelligence Index · rank 105 of 314
Unit
index score, higher is better
Configuration
GPT-6 Luna (medium)
Measured
1 Oct 2026
Not shown
Not business work, and a blend: read the parts for any one task.
Reported by Artificial Analysis
18.5
Artificial Analysis Intelligence Index · rank 192 of 314
Unit
index score, higher is better
Configuration
GPT-6 Luna (no reasoning)
Measured
1 Oct 2026
Not shown
Not business work, and a blend: read the parts for any one task.
Reported by Artificial Analysis
34.6
Artificial Analysis Intelligence Index · rank 75 of 314
Unit
index score, higher is better
Configuration
GPT-6 Luna (xhigh)
Measured
1 Oct 2026
Not shown
Not business work, and a blend: read the parts for any one task.
Reported by Artificial Analysis
32.9%
Humanity's Last Exam · rank 114 of 314
Unit
% of questions, higher is better
Configuration
GPT-6 Luna (high)
Measured
1 Oct 2026
Not shown
Not everyday work; academic questions at the edge of expertise.
Reported by Artificial Analysis
20.3%
Humanity's Last Exam · rank 163 of 314
Unit
% of questions, higher is better
Configuration
GPT-6 Luna (low)
Measured
1 Oct 2026
Not shown
Not everyday work; academic questions at the edge of expertise.
Reported by Artificial Analysis
38.5%
Humanity's Last Exam · rank 85 of 314
Unit
% of questions, higher is better
Configuration
GPT-6 Luna (max)
Measured
1 Oct 2026
Not shown
Not everyday work; academic questions at the edge of expertise.
Reported by Artificial Analysis
28.3%
Humanity's Last Exam · rank 132 of 314
Unit
% of questions, higher is better
Configuration
GPT-6 Luna (medium)
Measured
1 Oct 2026
Not shown
Not everyday work; academic questions at the edge of expertise.
Reported by Artificial Analysis
8.6%
Humanity's Last Exam · rank 242 of 314
Unit
% of questions, higher is better
Configuration
GPT-6 Luna (no reasoning)
Measured
1 Oct 2026
Not shown
Not everyday work; academic questions at the edge of expertise.
Reported by Artificial Analysis
34.3%
Humanity's Last Exam · rank 108 of 314
Unit
% of questions, higher is better
Configuration
GPT-6 Luna (xhigh)
Measured
1 Oct 2026
Not shown
Not everyday work; academic questions at the edge of expertise.
Reported by Artificial Analysis
79.3%
Long-context reasoning (AA-LCR) · rank 81 of 309
Unit
% of questions, higher is better
Configuration
GPT-6 Luna (high)
Measured
1 Oct 2026
Not shown
Not retrieval over your own document store.
Reported by Artificial Analysis
74.0%
Long-context reasoning (AA-LCR) · rank 137 of 309
Unit
% of questions, higher is better
Configuration
GPT-6 Luna (low)
Measured
1 Oct 2026
Not shown
Not retrieval over your own document store.
Reported by Artificial Analysis
83.3%
Long-context reasoning (AA-LCR) · rank 17 of 309
Unit
% of questions, higher is better
Configuration
GPT-6 Luna (max)
Measured
1 Oct 2026
Not shown
Not retrieval over your own document store.
Reported by Artificial Analysis
78.3%
Long-context reasoning (AA-LCR) · rank 93 of 309
Unit
% of questions, higher is better
Configuration
GPT-6 Luna (medium)
Measured
1 Oct 2026
Not shown
Not retrieval over your own document store.
Reported by Artificial Analysis
39.7%
Long-context reasoning (AA-LCR) · rank 258 of 309
Unit
% of questions, higher is better
Configuration
GPT-6 Luna (no reasoning)
Measured
1 Oct 2026
Not shown
Not retrieval over your own document store.
Reported by Artificial Analysis
80.0%
Long-context reasoning (AA-LCR) · rank 65 of 309
Unit
% of questions, higher is better
Configuration
GPT-6 Luna (xhigh)
Measured
1 Oct 2026
Not shown
Not retrieval over your own document store.
Reported by Artificial Analysis
50.3%
SciCode · rank 92 of 153
Unit
% of problems, higher is better
Configuration
GPT-6 Luna (high)
Measured
1 Oct 2026
Not shown
Not general software engineering.
Reported by Artificial Analysis
46.9%
SciCode · rank 108 of 153
Unit
% of problems, higher is better
Configuration
GPT-6 Luna (low)
Measured
1 Oct 2026
Not shown
Not general software engineering.
Reported by Artificial Analysis
54.6%
SciCode · rank 52 of 153
Unit
% of problems, higher is better
Configuration
GPT-6 Luna (max)
Measured
1 Oct 2026
Not shown
Not general software engineering.
Reported by Artificial Analysis
50.9%
SciCode · rank 87 of 153
Unit
% of problems, higher is better
Configuration
GPT-6 Luna (medium)
Measured
1 Oct 2026
Not shown
Not general software engineering.
Reported by Artificial Analysis
43.1%
SciCode · rank 121 of 153
Unit
% of problems, higher is better
Configuration
GPT-6 Luna (no reasoning)
Measured
1 Oct 2026
Not shown
Not general software engineering.
Reported by Artificial Analysis
51.7%
SciCode · rank 79 of 153
Unit
% of problems, higher is better
Configuration
GPT-6 Luna (xhigh)
Measured
1 Oct 2026
Not shown
Not general software engineering.
Reported by Artificial Analysis
4.5%
Terminal-Bench 4.0 · rank 89 of 150
Unit
% of tasks, higher is better
Configuration
GPT-6 Luna (high)
Measured
1 Oct 2026
Not shown
Not other harnesses or tools; one attempt per task.
Reported by Artificial Analysis
0.0%
Terminal-Bench 4.0 · rank 122 of 150
Unit
% of tasks, higher is better
Configuration
GPT-6 Luna (low)
Measured
1 Oct 2026
Not shown
Not other harnesses or tools; one attempt per task.
Reported by Artificial Analysis
12.6%
Terminal-Bench 4.0 · rank 65 of 150
Unit
% of tasks, higher is better
Configuration
GPT-6 Luna (max)
Measured
1 Oct 2026
Not shown
Not other harnesses or tools; one attempt per task.
Reported by Artificial Analysis
2.5%
Terminal-Bench 4.0 · rank 95 of 150
Unit
% of tasks, higher is better
Configuration
GPT-6 Luna (medium)
Measured
1 Oct 2026
Not shown
Not other harnesses or tools; one attempt per task.
Reported by Artificial Analysis
1.5%
Terminal-Bench 4.0 · rank 103 of 150
Unit
% of tasks, higher is better
Configuration
GPT-6 Luna (no reasoning)
Measured
1 Oct 2026
Not shown
Not other harnesses or tools; one attempt per task.
Reported by Artificial Analysis
8.1%
Terminal-Bench 4.0 · rank 78 of 150
Unit
% of tasks, higher is better
Configuration
GPT-6 Luna (xhigh)
Measured
1 Oct 2026
Not shown
Not other harnesses or tools; one attempt per task.
Reported by GDP.pdf
23.0%
Professional document tasks · rank 20 of 49
Unit
% of rubric, higher is better
Configuration
GPT-6 Luna (max)
Measured
1 Oct 2026
Not shown
Not your documents; 100 tasks, so small differences are noise.
Reported by SimpleQA Verified (Epoch AI)
41.4%
Correct answers · rank 41 of 85
Unit
% of questions, higher is better
Configuration
GPT-6 Luna (max)
Measured
22 Sep 2026
Not shown
Not answers grounded in your documents; tests what the model remembers.

Compare GPT-6 Luna with