THE SCOREBOARD FOR WHAT'S NEXTAI + QUANTUM, SCORED. COMPARED. EXPLAINED.
AIQUANTUMSCORE.

OpenAI / GPT-6

GPT-6 Luna

Version gpt-6-luna · Released 2026-09-22 · Available

Compare this model ↗
41QUANTUM SCORE

Explore OpenAI history →

THE PRACTICAL READ

Should you shortlist GPT-6 Luna?

Evidence checked 2026-11-07. This interpretation uses the cited records below; it is not a hands-on review.

What the evidence supports

The strongest relative category results in our current evidence are math and reasoning. Scores describe this comparison pool, not a percentage of real-world tasks solved.

12 current independent benchmark observations. Several tasks from one suite do not count as separate independent sources.

What remains uncertain

Comparable category scores are missing for multimodal. Writing quality, factual accuracy, privacy and production reliability require separate evaluation.

An overall score summarizes covered categories; a high overall score may not match your priorities. Check the effort level and tool configuration before comparing results.

Inspect coverage →

Cost and response time

At 10M input + 2M output tokens, the base API estimate is $2.00/month. This excludes tools, caching, batch rates, subscriptions and taxes.

Output tokens per second measures generation after it starts. Reasoning time can make a fast-generating model take longer to finish. Use the measured speed and effort records below.

Estimate your actual usage →

Alternatives worth comparing

Gemini 3.8 Flash

12 shared independent observations with matching test methods.

Same illustrative usage: $15.00/month. Lower price does not establish equivalent task performance.

Compare tradeoffs →

Grok 4.6

12 shared independent observations with matching test methods.

Same illustrative usage: $32.00/month. Lower price does not establish equivalent task performance.

Compare tradeoffs →

GPT-5.6 Terra

12 shared independent observations with matching test methods.

Same illustrative usage: $44.00/month. Lower price does not establish equivalent task performance.

Compare tradeoffs →

Follow changes to this model ↗ Choose an AI for coding → · Research guide → · Automation guide →

Coding33
Reasoning39
Math75
REVAL™
ⓘREVAL™ Research Evaluation Index — our proprietary 0–100 benchmark measuring real-world AI research performance. Methodology →
Not tested
Agents22
MultimodalNo data
Value41

PROPRIETARY / RESEARCH EVALUATION INDEX

REVAL™ Not tested

Methodology →

This exact model version has not completed a reviewed REVAL evaluation. No score is assigned from reputation or external benchmarks.

01 / EVIDENCE

Benchmark breakdown

BenchmarkVersionMethodConfigurationResultTest dateVerifiedSource typeSource
ARC-AGI-3 Semi-Private Standard harness best effort3 Semi-PrivateARC Prize Standard harness; best published effort per model—0.1942 %2026-09-292026-11-07benchmark maintainerView source ↗
LiveBench code_completion2026-06-25Public table; published model effort variantLiveBench public table 2026-06-25 · gpt-6-luna-max80.435 %not published2026-10-17benchmark maintainerView source ↗
LiveBench code_generation2026-06-25Public table; published model effort variantLiveBench public table 2026-06-25 · gpt-6-luna-max77.465 %not published2026-10-17benchmark maintainerView source ↗
LiveBench javascript2026-06-25Public table; published model effort variantLiveBench public table 2026-06-25 · gpt-6-luna-max63.636 %not published2026-10-17benchmark maintainerView source ↗
LiveBench AMPS_Hard2026-06-25Public table; published model effort variantLiveBench public table 2026-06-25 · gpt-6-luna-max98 %not published2026-10-17benchmark maintainerView source ↗
LiveBench olympiad2026-06-25Public table; published model effort variantLiveBench public table 2026-06-25 · gpt-6-luna-max90.376 %not published2026-10-17benchmark maintainerView source ↗
LiveBench theory_of_mind2026-06-25Public table; published model effort variantLiveBench public table 2026-06-25 · gpt-6-luna-max73.077 %not published2026-10-17benchmark maintainerView source ↗
LiveBench zebra_puzzle2026-06-25Public table; published model effort variantLiveBench public table 2026-06-25 · gpt-6-luna-max96 %not published2026-10-17benchmark maintainerView source ↗
Terminal-Bench 4.0 Vals mini-SWE-agent avg@3 fallbacks failed4.0Vals mini-SWE-agent avg@3; Anthropic fallbacks treated as failures— · max13.636 %not published2026-10-01independent labView source ↗
LiveBench 2.0 coding20261025LiveBench 2.0 published release tablePublished model configuration; effort not specified in table84.5 %not published2026-11-07benchmark maintainerView source ↗
LiveBench 2.0 reasoning20261025LiveBench 2.0 published release tablePublished model configuration; effort not specified in table81.8 %not published2026-11-07benchmark maintainerView source ↗
LiveBench 2.0 long_agentic20261025LiveBench 2.0 published release tablePublished model configuration; effort not specified in table30.9 %not published2026-11-07benchmark maintainerView source ↗

02 / COST

Price & speed

Input / 1M tokens $0.10

Output / 1M tokens $0.50

Cached input / 1M $0.01

Batch input / 1M $0.05

Batch output / 1M $0.25

Speed See measured observations below

Price verified 2026-10-19

Price scope Standard short-context token rate; long-context and service tiers differ

Price source Official pricing ↗

02A / PERFORMANCE

Measured speed

MetricResultEffortMethodSource
output tokens per second122.4 tokens/sMaxArtificial Analysis published model page; output generation after first chunk; provider configuration as stated; measurement date not publishedView source ↗

03 / PROFILE

Capabilities

tool usevision

04 / CONTEXT

Evidence coverage & limits

Published tests describe specific environments and effort settings. They do not establish performance on every task. Read the practical interpretation above →

Coverage: 73% · Moderate confidence · 12 observations · 4 source domains (4 independent).

05 / HISTORY

Version & price history

Version gpt-6-luna · released 2026-09-22.

2026-09-29: $0.10 input / $0.50 output per 1M tokens · Price source ↗

06 / SOURCES

Source records

DATED EVIDENCE

History

Standard API price history

2026-09-292026-09-29
  • 2026-09-29: 0.2 USD / 1M · 75% input / 25% output USD per 1M · source ↗

One observation; no trend can be inferred.

ARC-AGI-3 Semi-Private Standard harness best effort / 3 Semi-Private / %

2026-09-292026-09-29
  • 2026-09-29: 0.194 result · ARC Prize Standard harness; best published effort per model · source ↗

One observation; no trend can be inferred.

LiveBench code_completion / 2026-06-25 / %

2026-10-172026-10-17
  • 2026-10-17: 80.435 result · Public table; published model effort variant · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

LiveBench code_generation / 2026-06-25 / %

2026-10-172026-10-17
  • 2026-10-17: 77.465 result · Public table; published model effort variant · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

LiveBench javascript / 2026-06-25 / %

2026-10-172026-10-17
  • 2026-10-17: 63.636 result · Public table; published model effort variant · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

LiveBench AMPS_Hard / 2026-06-25 / %

2026-10-172026-10-17
  • 2026-10-17: 98 result · Public table; published model effort variant · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

LiveBench olympiad / 2026-06-25 / %

2026-10-172026-10-17
  • 2026-10-17: 90.376 result · Public table; published model effort variant · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

LiveBench theory_of_mind / 2026-06-25 / %

2026-10-172026-10-17
  • 2026-10-17: 73.077 result · Public table; published model effort variant · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

LiveBench zebra_puzzle / 2026-06-25 / %

2026-10-172026-10-17
  • 2026-10-17: 96 result · Public table; published model effort variant · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

Terminal-Bench 4.0 Vals mini-SWE-agent avg@3 fallbacks failed / 4.0 / %

2026-10-012026-10-01
  • 2026-10-01: 13.636 result · Vals mini-SWE-agent avg@3; Anthropic fallbacks treated as failures · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

LiveBench 2.0 coding / 20261025 / %

2026-11-072026-11-07
  • 2026-11-07: 84.5 result · LiveBench 2.0 published release table · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

LiveBench 2.0 reasoning / 20261025 / %

2026-11-072026-11-07
  • 2026-11-07: 81.8 result · LiveBench 2.0 published release table · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

LiveBench 2.0 long_agentic / 20261025 / %

2026-11-072026-11-07
  • 2026-11-07: 30.9 result · LiveBench 2.0 published release table · evaluation date not published; verification date shown · source ↗

One observation; no trend can be inferred.

output tokens per second / Max / tokens/s / Artificial Analysis published model page; output generation after first chunk; provider configuration as stated; measurement date not published

2026-10-012026-10-01
  • 2026-10-01: 122.4 measured · Artificial Analysis published model page; output generation after first chunk; provider configuration as stated; measurement date not published · measurement date not published; verification date shown · source ↗

One observation; no trend can be inferred.

coding category score history

2026-10-012026-11-07
  • 2026-10-01: 49 score · Scoring 3.0.0
  • 2026-10-02: 39 score · Scoring 3.0.0
  • 2026-10-03: 39 score · Scoring 3.0.0
  • 2026-10-04: 39 score · Scoring 3.0.0
  • 2026-10-05: 39 score · Scoring 3.0.0
  • 2026-10-06: 39 score · Scoring 3.0.0
  • 2026-10-07: 39 score · Scoring 3.0.0
  • 2026-10-08: 39 score · Scoring 3.0.0
  • 2026-10-09: 39 score · Scoring 3.0.0
  • 2026-10-10: 39 score · Scoring 3.0.0
  • 2026-10-11: 39 score · Scoring 3.0.0
  • 2026-10-12: 39 score · Scoring 3.0.0
  • 2026-10-13: 39 score · Scoring 3.0.0
  • 2026-10-14: 39 score · Scoring 3.0.0
  • 2026-10-15: 39 score · Scoring 3.0.0
  • 2026-10-16: 39 score · Scoring 3.0.0
  • 2026-10-17: 39 score · Scoring 3.0.0
  • 2026-10-18: 39 score · Scoring 3.0.0
  • 2026-10-19: 39 score · Scoring 3.0.0
  • 2026-10-20: 39 score · Scoring 3.0.0
  • 2026-10-21: 39 score · Scoring 3.0.0
  • 2026-10-22: 39 score · Scoring 3.0.0
  • 2026-10-23: 39 score · Scoring 3.0.0
  • 2026-10-24: 39 score · Scoring 3.0.0
  • 2026-10-25: 39 score · Scoring 3.0.0
  • 2026-10-26: 39 score · Scoring 3.0.0
  • 2026-10-27: 39 score · Scoring 3.0.0
  • 2026-10-28: 39 score · Scoring 3.0.0
  • 2026-10-29: 39 score · Scoring 3.0.0
  • 2026-10-30: 39 score · Scoring 3.0.0
  • 2026-10-31: 39 score · Scoring 3.0.0
  • 2026-11-01: 39 score · Scoring 3.0.0
  • 2026-11-02: 39 score · Scoring 3.0.0
  • 2026-11-03: 39 score · Scoring 3.0.0
  • 2026-11-04: 39 score · Scoring 3.0.0
  • 2026-11-05: 39 score · Scoring 3.0.0
  • 2026-11-06: 39 score · Scoring 3.0.0
  • 2026-11-07: 39 score · Scoring 3.0.0

reasoning category score history

2026-09-302026-11-07
  • 2026-09-30: 0 score · Scoring 3.0.0
  • 2026-10-01: 52 score · Scoring 3.0.0
  • 2026-10-02: 52 score · Scoring 3.0.0
  • 2026-10-03: 52 score · Scoring 3.0.0
  • 2026-10-04: 52 score · Scoring 3.0.0
  • 2026-10-05: 52 score · Scoring 3.0.0
  • 2026-10-06: 52 score · Scoring 3.0.0
  • 2026-10-07: 52 score · Scoring 3.0.0
  • 2026-10-08: 52 score · Scoring 3.0.0
  • 2026-10-09: 52 score · Scoring 3.0.0
  • 2026-10-10: 52 score · Scoring 3.0.0
  • 2026-10-11: 52 score · Scoring 3.0.0
  • 2026-10-12: 52 score · Scoring 3.0.0
  • 2026-10-13: 52 score · Scoring 3.0.0
  • 2026-10-14: 52 score · Scoring 3.0.0
  • 2026-10-15: 52 score · Scoring 3.0.0
  • 2026-10-16: 52 score · Scoring 3.0.0
  • 2026-10-17: 52 score · Scoring 3.0.0
  • 2026-10-18: 52 score · Scoring 3.0.0
  • 2026-10-19: 52 score · Scoring 3.0.0
  • 2026-10-20: 52 score · Scoring 3.0.0
  • 2026-10-21: 52 score · Scoring 3.0.0
  • 2026-10-22: 52 score · Scoring 3.0.0
  • 2026-10-23: 52 score · Scoring 3.0.0
  • 2026-10-24: 52 score · Scoring 3.0.0
  • 2026-10-25: 52 score · Scoring 3.0.0
  • 2026-10-26: 52 score · Scoring 3.0.0
  • 2026-10-27: 52 score · Scoring 3.0.0
  • 2026-10-28: 52 score · Scoring 3.0.0
  • 2026-10-29: 52 score · Scoring 3.0.0
  • 2026-10-30: 52 score · Scoring 3.0.0
  • 2026-10-31: 52 score · Scoring 3.0.0
  • 2026-11-01: 52 score · Scoring 3.0.0
  • 2026-11-02: 52 score · Scoring 3.0.0
  • 2026-11-03: 52 score · Scoring 3.0.0
  • 2026-11-04: 52 score · Scoring 3.0.0
  • 2026-11-05: 52 score · Scoring 3.0.0
  • 2026-11-06: 52 score · Scoring 3.0.0
  • 2026-11-07: 52 score · Scoring 3.0.0

math category score history

2026-10-012026-11-07
  • 2026-10-01: 75 score · Scoring 3.0.0
  • 2026-10-02: 75 score · Scoring 3.0.0
  • 2026-10-03: 75 score · Scoring 3.0.0
  • 2026-10-04: 75 score · Scoring 3.0.0
  • 2026-10-05: 75 score · Scoring 3.0.0
  • 2026-10-06: 75 score · Scoring 3.0.0
  • 2026-10-07: 75 score · Scoring 3.0.0
  • 2026-10-08: 75 score · Scoring 3.0.0
  • 2026-10-09: 75 score · Scoring 3.0.0
  • 2026-10-10: 75 score · Scoring 3.0.0
  • 2026-10-11: 75 score · Scoring 3.0.0
  • 2026-10-12: 75 score · Scoring 3.0.0
  • 2026-10-13: 75 score · Scoring 3.0.0
  • 2026-10-14: 75 score · Scoring 3.0.0
  • 2026-10-15: 75 score · Scoring 3.0.0
  • 2026-10-16: 75 score · Scoring 3.0.0
  • 2026-10-17: 75 score · Scoring 3.0.0
  • 2026-10-18: 75 score · Scoring 3.0.0
  • 2026-10-19: 75 score · Scoring 3.0.0
  • 2026-10-20: 75 score · Scoring 3.0.0
  • 2026-10-21: 75 score · Scoring 3.0.0
  • 2026-10-22: 75 score · Scoring 3.0.0
  • 2026-10-23: 75 score · Scoring 3.0.0
  • 2026-10-24: 75 score · Scoring 3.0.0
  • 2026-10-25: 75 score · Scoring 3.0.0
  • 2026-10-26: 75 score · Scoring 3.0.0
  • 2026-10-27: 75 score · Scoring 3.0.0
  • 2026-10-28: 75 score · Scoring 3.0.0
  • 2026-10-29: 75 score · Scoring 3.0.0
  • 2026-10-30: 75 score · Scoring 3.0.0
  • 2026-10-31: 75 score · Scoring 3.0.0
  • 2026-11-01: 75 score · Scoring 3.0.0
  • 2026-11-02: 75 score · Scoring 3.0.0
  • 2026-11-03: 75 score · Scoring 3.0.0
  • 2026-11-04: 75 score · Scoring 3.0.0
  • 2026-11-05: 75 score · Scoring 3.0.0
  • 2026-11-06: 75 score · Scoring 3.0.0
  • 2026-11-07: 75 score · Scoring 3.0.0

agents category score history

2026-10-012026-11-07
  • 2026-10-01: 20 score · Scoring 3.0.0
  • 2026-10-02: 20 score · Scoring 3.0.0
  • 2026-10-03: 20 score · Scoring 3.0.0
  • 2026-10-04: 20 score · Scoring 3.0.0
  • 2026-10-05: 20 score · Scoring 3.0.0
  • 2026-10-06: 20 score · Scoring 3.0.0
  • 2026-10-07: 20 score · Scoring 3.0.0
  • 2026-10-08: 20 score · Scoring 3.0.0
  • 2026-10-09: 20 score · Scoring 3.0.0
  • 2026-10-10: 20 score · Scoring 3.0.0
  • 2026-10-11: 20 score · Scoring 3.0.0
  • 2026-10-12: 20 score · Scoring 3.0.0
  • 2026-10-13: 20 score · Scoring 3.0.0
  • 2026-10-14: 20 score · Scoring 3.0.0
  • 2026-10-15: 20 score · Scoring 3.0.0
  • 2026-10-16: 20 score · Scoring 3.0.0
  • 2026-10-17: 20 score · Scoring 3.0.0
  • 2026-10-18: 20 score · Scoring 3.0.0
  • 2026-10-19: 20 score · Scoring 3.0.0
  • 2026-10-20: 20 score · Scoring 3.0.0
  • 2026-10-21: 20 score · Scoring 3.0.0
  • 2026-10-22: 20 score · Scoring 3.0.0
  • 2026-10-23: 20 score · Scoring 3.0.0
  • 2026-10-24: 20 score · Scoring 3.0.0
  • 2026-10-25: 20 score · Scoring 3.0.0
  • 2026-10-26: 20 score · Scoring 3.0.0
  • 2026-10-27: 20 score · Scoring 3.0.0
  • 2026-10-28: 20 score · Scoring 3.0.0
  • 2026-10-29: 20 score · Scoring 3.0.0
  • 2026-10-30: 20 score · Scoring 3.0.0
  • 2026-10-31: 20 score · Scoring 3.0.0
  • 2026-11-01: 20 score · Scoring 3.0.0
  • 2026-11-02: 20 score · Scoring 3.0.0
  • 2026-11-03: 20 score · Scoring 3.0.0
  • 2026-11-04: 20 score · Scoring 3.0.0
  • 2026-11-05: 20 score · Scoring 3.0.0
  • 2026-11-06: 20 score · Scoring 3.0.0
  • 2026-11-07: 20 score · Scoring 3.0.0

07 / EXPLORE

Similar models