BlogLLM Benchmark Scores as Published, Side by Side

GPT-6 Astra vs Claude Fable 5.2: Benchmark Scores Side by Side

Every test both GPT-6 Astra by OpenAI and Claude Fable 5.2 by Anthropic have a published number for: 32 tests in 8 areas. Each number is as printed, with the page it comes from and the setup it was run under; nothing is ranked or rescored, and two numbers under different setups are two results, not one comparison.

Models GPT-6 Astra, Claude Fable 5.2Data version 2026111201, as of 2026-11-12

Model

What each developer prints on its own model page; a dash means it prints none.

FactGPT-6 AstraClaude Fable 5.2
Released2026-09-032026-11-09
Context window1.05M1M
Max output128K128K
InputText, imageText, image
OutputTextText
WeightsClosedClosed

Knowledge Work

TestGPT-6 AstraClaude Fable 5.2
AutomationBench
41.4%OpenAI, GPT-6 Astra, checked 2026-10-14; printed on 9 more pages
51.4%Anthropic, Claude Fable 5.2 and Mythos 5.2, checked 2026-11-09; printed on 1 more page
OfficeQA Pro
66.2%Moonshot AI, Introducing Kimi K3.1 Pro, checked 2026-10-24Effort: max; Harness: Codex; Fallback: with fallback
GDPval-AA v2.1
1584Anthropic, System Card: Claude Fable 5.2 & Claude Mythos 5.2, checked 2026-11-09; printed on 4 more pages
AA-Briefcase v1.1
1569Anthropic, Claude Fable 5.2 and Mythos 5.2, checked 2026-11-09; printed on 3 more pages
1785Anthropic, Claude Fable 5.2 and Mythos 5.2, checked 2026-11-09; printed on 1 more page
Harvey LAB-AA v1.1 (hallucination-gated all-pass rate)
8.6%Anthropic, System Card: Claude Fable 5.2 & Claude Mythos 5.2, checked 2026-11-09; printed on 1 more page
AA-Briefcase v1.1 (rubric pass rate)
52%Anthropic, Claude Fable 5.2 and Mythos 5.2, checked 2026-11-09; printed on 1 more page
66.1%Anthropic, Claude Fable 5.2 and Mythos 5.2, checked 2026-11-09; printed on 1 more page
Remote Labor Index (automation rate)
20.8%Anthropic, Claude Fable 5.2 and Mythos 5.2, checked 2026-11-09; printed on 1 more page
41.3%Anthropic, Claude Fable 5.2 and Mythos 5.2, checked 2026-11-09; printed on 1 more pageEffort: high

Agentic Coding

TestGPT-6 AstraClaude Fable 5.2
DeepSWE v1.1
74.1%OpenAI, GPT-6 Astra, checked 2026-10-14; printed on 3 more pages
Terminal-Bench 4.0
57.9%OpenAI, GPT-6 Astra, checked 2026-10-14; printed on 8 more pages
67.6%Anthropic, System Card: Claude Fable 5.2 & Claude Mythos 5.2, checked 2026-11-09Effort: max; Harness: Claude Code --bare; Fallback: safeguards on; the fallback answered 2.5% of requests, affecting 10% of trials
FrontierSWE v2
65.5%Anthropic, Claude Fable 5.2 and Mythos 5.2, checked 2026-11-09; printed on 5 more pages
69.9%Anthropic, Claude Fable 5.2 and Mythos 5.2, checked 2026-11-09; printed on 1 more page
Vibe Code Bench
89.6%Google, Gemini 4 Argon, checked 2026-10-29
93.77%Vals AI, Vibe Code Bench v1.1 leaderboard, checked 2026-11-09Harness: OpenHands
FrontierCode 2.0
42.8%Anthropic, Claude Fable 5.2 and Mythos 5.2, checked 2026-11-09; printed on 1 more page
49.1%Anthropic, Claude Fable 5.2 and Mythos 5.2, checked 2026-11-09; printed on 1 more pageEffort: xhigh
FrontierCode 2.0 (average cost per task)lower is better
$6.68Anthropic, System Card: Claude Fable 5.2 & Claude Mythos 5.2, checked 2026-11-09Effort: max; Harness: Codex CLI
$2.48Anthropic, System Card: Claude Fable 5.2 & Claude Mythos 5.2, checked 2026-11-09Effort: medium; Harness: Claude Code
$44.7Anthropic, System Card: Claude Fable 5.2 & Claude Mythos 5.2, checked 2026-11-09Effort: max; Harness: Claude Code
$6.72Anthropic, System Card: Claude Fable 5.2 & Claude Mythos 5.2, checked 2026-11-09Effort: high; Harness: Claude Code
$14.19Anthropic, System Card: Claude Fable 5.2 & Claude Mythos 5.2, checked 2026-11-09Effort: xhigh; Harness: Claude Code
$2.1Anthropic, System Card: Claude Fable 5.2 & Claude Mythos 5.2, checked 2026-11-09Effort: low; Harness: Claude Code

Science and Math

TestGPT-6 AstraClaude Fable 5.2
GPQA Diamond
96%OpenAI, GPT-6 Astra, checked 2026-10-14; printed on 1 more page
93.9%Epoch AI, Epoch AI Benchmarking Hub, checked 2026-11-10Effort: max
Terminal-Bench Science 0.1
64.6%OpenAI, GPT-6 Astra, checked 2026-10-14; printed on 9 more pages
74.6%Anthropic, Claude Fable 5.2 and Mythos 5.2, checked 2026-11-09; printed on 1 more page
FrontierMath Tier 4 (v2)
97.6%OpenAI, GPT-6 Astra, checked 2026-10-14
100%Epoch AI, Epoch AI Benchmarking Hub, checked 2026-11-10Effort: max
FrontierMath Tier 1-3 (v2)
93.7%Epoch AI, Epoch AI Benchmarking Hub, checked 2026-10-30Effort: max
95.1%Epoch AI, Epoch AI Benchmarking Hub, checked 2026-11-10Effort: max

Computer Use

TestGPT-6 AstraClaude Fable 5.2
OSWorld 2.1 offline subset
79.5%Anthropic, Claude Fable 5.2 and Mythos 5.2, checked 2026-11-09; printed on 2 more pages
89.3%Anthropic, Claude Fable 5.2 and Mythos 5.2, checked 2026-11-09; printed on 1 more page
OSWorld 2.1 binary
34.3%Meta, Meta Muse Wonder model card, checked 2026-10-19Effort: max

Multimodal Understanding

TestGPT-6 AstraClaude Fable 5.2
Chartography (no tools)
71%Anthropic, Claude Fable 5.2 and Mythos 5.2, checked 2026-11-09; printed on 3 more pages
73.4%Anthropic, Claude Fable 5.2 and Mythos 5.2, checked 2026-11-09; printed on 1 more page
Chartography (with tools)
91%Moonshot AI, Introducing Kimi K3.1 Pro, checked 2026-10-24Effort: max; Tools: python; Fallback: with fallback

General Knowledge and Reasoning

TestGPT-6 AstraClaude Fable 5.2
Humanity's Last Exam (no tools)
53.6%Moonshot AI, Introducing Kimi K3.1 Pro, checked 2026-10-24Effort: max; Tools: none; Fallback: with fallback
Humanity's Last Exam (with tools)
57.2%OpenAI, GPT-6 Astra, checked 2026-10-14; printed on 5 more pagesTools: enabled; exact tools in source
74.2%Anthropic, Claude Fable 5.2 and Mythos 5.2, checked 2026-11-09; printed on 1 more page
SimpleQA Verified
75.6%Epoch AI, Epoch AI Benchmarking Hub, checked 2026-10-30Effort: max
94%Epoch AI, Epoch AI Benchmarking Hub, checked 2026-11-10Effort: max
ARC-AGI-3
99.9%OpenAI, GPT-6 Astra, checked 2026-10-14; printed on 1 more page
79.26%Anthropic, System Card: Claude Fable 5.2 & Claude Mythos 5.2, checked 2026-11-09Effort: high; Harness: Standard
65.66%Anthropic, System Card: Claude Fable 5.2 & Claude Mythos 5.2, checked 2026-11-09Effort: max; Harness: Standard
ARC-AGI-3 (Provider Adapter harness)
98.6%Anthropic, System Card: Claude Fable 5.2 & Claude Mythos 5.2, checked 2026-11-09Effort: max; Harness: Provider Adapter
97.72%Anthropic, System Card: Claude Fable 5.2 & Claude Mythos 5.2, checked 2026-11-09Effort: high; Harness: Provider Adapter
94.9%Anthropic, System Card: Claude Fable 5.2 & Claude Mythos 5.2, checked 2026-11-09Effort: max; Harness: Provider Adapter

Healthcare

TestGPT-6 AstraClaude Fable 5.2
HealthBench
58.3OpenAI, GPT-6 Astra System Card, checked 2026-10-25; printed on 2 more pages
HealthBench Professional (length-adjusted)
63.4%OpenAI, GPT-6 Astra, checked 2026-10-14; printed on 5 more pages
HealthBench (unadjusted)
56.9OpenAI, GPT-6.1 Sol system card addendum, checked 2026-10-19; printed on 1 more page
HealthBench Professional (unadjusted)
68.2%OpenAI, GPT-6.1 Sol system card addendum, checked 2026-10-19; printed on 1 more page
PhysicianBench
55%Anthropic, System Card: Claude Fable 5.2 & Claude Mythos 5.2, checked 2026-11-09Effort: high; Attempt budget: 1 attempt
48%Anthropic, System Card: Claude Fable 5.2 & Claude Mythos 5.2, checked 2026-11-09Effort: max; Attempt budget: 1 attempt
64.4%Anthropic, System Card: Claude Fable 5.2 & Claude Mythos 5.2, checked 2026-11-09Effort: max; Attempt budget: 5 attempts

Engineering and Design

TestGPT-6 AstraClaude Fable 5.2
RoboDojo Sim

Price

API list prices in US dollars per one million tokens, as printed on the developer's pricing page on the day checked; a dash means the developer lists that price in another unit or not at all. Cost per task is measured by Vals AI.

PriceGPT-6 AstraClaude Fable 5.2
Input
$10OpenAI, OpenAI API pricing, checked 2026-10-15Context: up to 272,000 tokens; Long context: $20 per 1M tokens above 272,000 tokens
$8Anthropic, Anthropic API pricing, checked 2026-11-09
Cached input
$1OpenAI, OpenAI API pricing, checked 2026-10-15Context: up to 272,000 tokens; Long context: $2 per 1M tokens above 272,000 tokens
$0.2Anthropic, Anthropic API pricing, checked 2026-11-09
Cache write
$12.5OpenAI, OpenAI API pricing, checked 2026-10-15Context: up to 272,000 tokens; Long context: $25 per 1M tokens above 272,000 tokens
$10Anthropic, Anthropic API pricing, checked 2026-11-09Cache: 5 minute cache
Cache write, 1 hour-
$16Anthropic, Anthropic API pricing, checked 2026-11-09
Output
$50OpenAI, OpenAI API pricing, checked 2026-10-15Context: up to 272,000 tokens; Long context: $75 per 1M tokens above 272,000 tokens
$40Anthropic, Anthropic API pricing, checked 2026-11-09
Input, batch
$5OpenAI, OpenAI API pricing, checked 2026-10-15Context: up to 272,000 tokens; Long context: $10 per 1M tokens above 272,000 tokens
$4Anthropic, Anthropic API pricing, checked 2026-11-09
Cached input, batch
$0.5OpenAI, OpenAI API pricing, checked 2026-10-15Context: up to 272,000 tokens; Long context: $1 per 1M tokens above 272,000 tokens
-
Cache write, batch
$6.25OpenAI, OpenAI API pricing, checked 2026-10-15Context: up to 272,000 tokens; Long context: $12.5 per 1M tokens above 272,000 tokens
-
Output, batch
$25OpenAI, OpenAI API pricing, checked 2026-10-15Context: up to 272,000 tokens; Long context: $37.5 per 1M tokens above 272,000 tokens
$20Anthropic, Anthropic API pricing, checked 2026-11-09
Input, flex
$5OpenAI, OpenAI API pricing, checked 2026-10-15Context: up to 272,000 tokens; Long context: $10 per 1M tokens above 272,000 tokens
-
Cached input, flex
$0.5OpenAI, OpenAI API pricing, checked 2026-10-15Context: up to 272,000 tokens; Long context: $1 per 1M tokens above 272,000 tokens
-
Cache write, flex
$6.25OpenAI, OpenAI API pricing, checked 2026-10-15Context: up to 272,000 tokens; Long context: $12.5 per 1M tokens above 272,000 tokens
-
Output, flex
$25OpenAI, OpenAI API pricing, checked 2026-10-15Context: up to 272,000 tokens; Long context: $37.5 per 1M tokens above 272,000 tokens
-
Input, fast
$20OpenAI, OpenAI API pricing, checked 2026-10-15Context: up to 272,000 tokens; Long context: $40 per 1M tokens above 272,000 tokens
$16Anthropic, Anthropic API pricing, checked 2026-11-09
Cached input, fast
$2OpenAI, OpenAI API pricing, checked 2026-10-15Context: up to 272,000 tokens; Long context: $4 per 1M tokens above 272,000 tokens
-
Cache write, fast
$25OpenAI, OpenAI API pricing, checked 2026-10-15Context: up to 272,000 tokens; Long context: $50 per 1M tokens above 272,000 tokens
-
Output, fast
$100OpenAI, OpenAI API pricing, checked 2026-10-15Context: up to 272,000 tokens; Long context: $150 per 1M tokens above 272,000 tokens
$80Anthropic, Anthropic API pricing, checked 2026-11-09
Input, ultrafast
$60OpenAI, OpenAI API pricing, checked 2026-10-15Context: up to 272,000 tokens; Long context: $120 per 1M tokens above 272,000 tokens
-
Cached input, ultrafast
$6OpenAI, OpenAI API pricing, checked 2026-10-15Context: up to 272,000 tokens; Long context: $12 per 1M tokens above 272,000 tokens
-
Cache write, ultrafast
$75OpenAI, OpenAI API pricing, checked 2026-10-15Context: up to 272,000 tokens; Long context: $150 per 1M tokens above 272,000 tokens
-
Output, ultrafast
$300OpenAI, OpenAI API pricing, checked 2026-10-15Context: up to 272,000 tokens; Long context: $450 per 1M tokens above 272,000 tokens
-
Cost per taskVals AI, USD, lower is better
$38.51Vals AI, Vibe Code Bench v1.1 leaderboard, checked 2026-10-27Harness: OpenHands
$22.13Vals AI, Vibe Code Bench v1.1 leaderboard, checked 2026-11-09Harness: OpenHands

GPT-6 Astra has 179 more and Claude Fable 5.2 has 14 more: tests only one of them has a number for, listed on its model page.

More side by side

Every number here is read from the same catalog file as the benchmark table, data version 2026111201. A pair has a page when both models are their developers' flagships and both have a number for at least 10 of the same tests. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.