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

HEAD TO HEAD

Make the
right call.

Pick two to four models. Compare category evidence, price, context, speed and capabilities side by side.

Sign in to save this comparison →

01 / SCORECARD

Coding focus · side by side

MetricGPT-6 AstraGPT-6 Sol
Quantum Score60QUANTUM SCORE48QUANTUM SCORE
Confidence / coverageModerate confidence · 73% · 4 independent domainsModerate confidence · 73% · 3 independent domains
Context window1,050,000 tokens1,050,000 tokens
Modalities / toolstext, image · tool use, visiontext, image · tool use, vision
Coding6339 -24 vs first
Reasoning9867 -31 vs first
Math8779 -8 vs first
Research——
Agents2020 +0 vs first
Multimodal——
Speed——
Value2237 +15 vs first
Input / 1M$10.00$2.00
Output / 1M$50.00$10.00
Measured output speed55 tokens/s · Max effort—

02 / EVIDENCE

Published benchmark evidence

BenchmarkGPT-6 AstraGPT-6 Sol
ARC-AGI-3 Semi-Private Standard harness best effort · 3 Semi-Private · ARC Prize Standard harness; best published effort per model62.7128 %
benchmark maintainer ↗
4.6236 %
benchmark maintainer ↗
ProgramBench Vals 200 public tasks raw pass rate · Vals 2026-09-27 · Vals 200 public tasks; raw pass rate; mini-SWE-agent85.4 %
independent lab ↗
81.9 %
independent lab ↗
LiveBench code_completion · 2026-06-25 · Public table; published model effort variant80.435 %
benchmark maintainer ↗
80.435 %
benchmark maintainer ↗
LiveBench code_generation · 2026-06-25 · Public table; published model effort variant80.282 %
benchmark maintainer ↗
83.099 %
benchmark maintainer ↗
LiveBench javascript · 2026-06-25 · Public table; published model effort variant63.636 %
benchmark maintainer ↗
63.636 %
benchmark maintainer ↗
LiveBench AMPS_Hard · 2026-06-25 · Public table; published model effort variant98 %
benchmark maintainer ↗
98 %
benchmark maintainer ↗
LiveBench olympiad · 2026-06-25 · Public table; published model effort variant92.166 %
benchmark maintainer ↗
91.365 %
benchmark maintainer ↗
LiveBench theory_of_mind · 2026-06-25 · Public table; published model effort variant84.615 %
benchmark maintainer ↗
84.615 %
benchmark maintainer ↗
LiveBench zebra_puzzle · 2026-06-25 · Public table; published model effort variant100 %
benchmark maintainer ↗
100 %
benchmark maintainer ↗

AS THE EVIDENCE CHANGED

Comparison history

Dated releases, price events, and benchmark publications. A price or test change can alter the factual comparison; this timeline does not pick a winner.

2026-09-22 · GPT-6 Sol and Luna added to the API ↗ · source

2026-09-03 · GPT-6 Astra released ↗ · source

2026-09-30 verified (test date not published) · gpt-6-astra entered LiveBench code_completion (2026-06-25) at 80.435 % · source ↗

2026-09-30 verified (test date not published) · gpt-6-astra entered LiveBench code_generation (2026-06-25) at 80.282 % · source ↗

2026-09-30 verified (test date not published) · gpt-6-astra entered LiveBench javascript (2026-06-25) at 63.636 % · source ↗

2026-09-30 verified (test date not published) · gpt-6-astra entered LiveBench AMPS_Hard (2026-06-25) at 98 % · source ↗

2026-09-30 verified (test date not published) · gpt-6-astra entered LiveBench olympiad (2026-06-25) at 92.166 % · source ↗

2026-09-30 verified (test date not published) · gpt-6-astra entered LiveBench theory_of_mind (2026-06-25) at 84.615 % · source ↗

2026-09-30 verified (test date not published) · gpt-6-astra entered LiveBench zebra_puzzle (2026-06-25) at 100 % · source ↗

2026-09-30 verified (test date not published) · gpt-6-sol entered LiveBench code_completion (2026-06-25) at 80.435 % · source ↗

2026-09-30 verified (test date not published) · gpt-6-sol entered LiveBench code_generation (2026-06-25) at 83.099 % · source ↗

2026-09-30 verified (test date not published) · gpt-6-sol entered LiveBench javascript (2026-06-25) at 63.636 % · source ↗

2026-09-30 verified (test date not published) · gpt-6-sol entered LiveBench AMPS_Hard (2026-06-25) at 98 % · source ↗

2026-09-30 verified (test date not published) · gpt-6-sol entered LiveBench olympiad (2026-06-25) at 91.365 % · source ↗

An overall score appears only after enough current, comparable, independently sourced results exist. Pricing and individual benchmark results remain visible meanwhile.