Scoring changed to Quality v3. Pages are now scored out of 100 from a full test of how they work, how they look and how they are built, not from one screenshot, and every result on this site has been rescored. Read more about this change

Home › Videos › Claude Fable 5.2 Tested: 84.46 on the Quality v3 Core Tests, First of 14

10 Nov 2026 · 3 runs · 3 models

Claude Fable 5.2 Tested: 84.46 on the Quality v3 Core Tests, First of 14

Claude Fable 5.2 at high effort through Claude Code, on the five core tests and the wildcard. It scored 84.46 on the five core tests, first of 14 runs on the equivalent core tests, 4.7 points ahead of GPT-6 Astra (79.75, inside the 5-point tie band) and 5.1 ahead of Claude Opus 5.5 (79.33). All six pages were scored, none failed. The five core tests took 2 h 25 m of generation and cost $51.95 at API prices, about $10.39 a test.

The results

The same scores as the leaderboard: a test that failed is left out of its run's score, not counted as zero. Time, tokens and cost cover each whole run, wildcards included.

See the whole board

Ranking

Quality v3 over measured non-wildcard pages. Different workloads: browse the outputs and coverage before comparing models.

1
claude-fable-5-2effort: highAnthropic · 5/5 scored pages
84
2
claude-opus-5-5effort: highAnthropic · 8/8 scored pages
82
3
gpt-6-astraeffort: highOpenAI · 8/8 scored pages
81
050100

Score against output tokens

Quality v3 against full-run tokens. Different workloads and hardware affect this comparison.

Claude FableClaude OpusGPT Astra
7075808590950500k1M1.5M Output tokens across all tests, thinking included Average score (out of 100) gpt-6-astra (OpenAI): 81 / 100, 322k output tokensclaude-fable-5-2 (Anthropic): 84 / 100, 906k output tokensclaude-opus-5-5 (Anthropic): 82 / 100, 1.30M output tokensgpt-6-astra (OpenAI): 81 / 100, 322k output tokensgpt-6-astra · highclaude-fable-5-2 (Anthropic): 84 / 100, 906k output tokensclaude-fable-5-2 · highclaude-opus-5-5 (Anthropic): 82 / 100, 1.30M output tokensclaude-opus-5-5 · high

Output tokens include the model's thinking. Like the time, tokens and cost table, it counts every test the model took, wildcards included. The score axis is zoomed to the data.

Score against time

Quality v3 against full-run time. Different workloads and hardware affect this comparison.

Claude FableClaude OpusGPT Astra
70758085909501h2h3h4h Time taken across all tests, thinking included Average score (out of 100) claude-fable-5-2 (Anthropic): 84 / 100, 2h 35mclaude-opus-5-5 (Anthropic): 82 / 100, 3h 29mgpt-6-astra (OpenAI): 81 / 100, 3h 31mclaude-fable-5-2 (Anthropic): 84 / 100, 2h 35mclaude-fable-5-2 · highclaude-opus-5-5 (Anthropic): 82 / 100, 3h 29mclaude-opus-5-5 · highgpt-6-astra (OpenAI): 81 / 100, 3h 31mgpt-6-astra · high

Time is how long the model took to answer, added up over its tests; judging is not counted. Like the time, tokens and cost table, it counts every test the model took, wildcards included. The score axis is zoomed to the data.

Where each model is strong and weak

One row per model, one column per test and per scoring criterion.

By testBy what the judges scored
ModelAero LabJet OdysseyBlast IslandLaunch DayAlex OpticsAfterburnerHangar OpsHangar PlannerRotor RampageBrief deliveredWorking behaviourLook and feelEngineering quality
claude-fable-5-2effort: high8884857790————931007065
claude-opus-5-5effort: high89798479668689—8190967163
gpt-6-astraeffort: high838280698581—897992996850
Violet is strong, orange is weak, on the same 0–100 scale in every cell.Different prompts and protocols: no best-in-column verdict.

Time, tokens and cost

What each model used across all its tests, wildcards included.

ModelTestsTimeOutput tokensSpeedCostSubscription used
claude-fable-5-2effort: highAnthropic 6 2h 35m 906k547k of it thinking 97.2 tok/s $55.39API price 7-day window +6 pts
claude-opus-5-5effort: highAnthropic 8 3h 29m 1.30M753k of it thinking 103.0 tok/s $36.60API price 5-hour window not comparable7-day window +2 pts
gpt-6-astraeffort: highOpenAI 9 3h 31m 322k75k of it thinking 25.4 tok/s ≈$31.69API price, est. —
≈ An estimate: the provider reported no count, so it is worked out from the length of the output (about 4 characters a token). — Not measured. Cost says how it was worked out: charged by the provider, at API prices (for a subscription), or no API charge on local hardware. ≥ means some tests had no price.

Read from the account's usage window in whole percentage points, so a short run can show 0 points. It counts everything the account did in that time, not only this run.

Runs in this video

Every run behind the numbers. Scores name their comparison basis.

Model
Score / basis
Time
Output tokens
Cost
claude-fable-5-2effort: highAnthropic · 10 Nov 2026
84 / 100Quality v3 · 5/5 pages
Time2h 35m
Output tokens906k
Cost$55.39API price
claude-opus-5-5effort: highAnthropic · 3 Oct 2026
82 / 100Quality v3 · 8/8 pages
Time3h 29m
Output tokens1.30M
Cost$36.60API price
gpt-6-astraeffort: highOpenAI · 3 Oct 2026
81 / 100Quality v3 · 8/8 pages
Time3h 31m
Output tokens322k
Cost≈$31.69API price, est.

claude-fable-5-2effort: high

Anthropic · 84 / 100 · Quality v3 · 5/5 pages · 2h 35m · $55.39

Screenshot of the page claude-fable-5-2 made for Aero Lab88
Aero Lab claude-fable-5-2 · effort: high 22m 38s · 130k tokens · $7.46 Quality v3 · Brief delivered 97 · Working behaviour 100 · Look and feel 76 · Engineering quality 64scored by claude-code/claude-opus-5-5 (quality-3 rubric)prompt 1e8e809e8caeb2ba
How this score was reached…
Open the pageDetails
Screenshot of the page claude-fable-5-2 made for Jet Odyssey84
Jet Odyssey claude-fable-5-2 · effort: high 36m 22s · 215k tokens · $13.97 Quality v3 · Brief delivered 93 · Working behaviour 100 · Look and feel 64 · Engineering quality 64scored by claude-code/claude-opus-5-5 (quality-3 rubric)prompt 1ce617b6d67089b2
How this score was reached…
Open the pageDetails
Screenshot of the page claude-fable-5-2 made for Blast Island85
Blast Island claude-fable-5-2 · effort: high 20m 58s · 126k tokens · $7.84 Quality v3 · Brief delivered 94 · Working behaviour 100 · Look and feel 71 · Engineering quality 58scored by claude-code/claude-opus-5-5 (quality-3 rubric)prompt 28ba22cd0f56ca1e
How this score was reached…
Open the pageDetails
Screenshot of the page claude-fable-5-2 made for Launch Day77
Launch Day claude-fable-5-2 · effort: high 37m 40s · 217k tokens · $13.53 Quality v3 · Brief delivered 82 · Working behaviour 100 · Look and feel 61 · Engineering quality 65scored by claude-code/claude-opus-5-5 (quality-3 rubric)prompt d1e76d48a7ac8eb6
How this score was reached…
Open the pageDetails
Screenshot of the page claude-fable-5-2 made for Alex Optics90
Alex Optics claude-fable-5-2 · effort: high 27m 41s · 157k tokens · $9.15 Quality v3 · Brief delivered 100 · Working behaviour 100 · Look and feel 76 · Engineering quality 72scored by claude-code/claude-opus-5-5 (quality-3 rubric)prompt de7c304e41dd3505
How this score was reached…
Open the pageDetails
Screenshot of the page claude-fable-5-2 made for Rose Window Derby81
Rose Window Derbywildcard claude-fable-5-2 · effort: high 10m 01s · 61k tokens · $3.44 Quality v3 · Brief delivered 86 · Working behaviour 100 · Look and feel 63 · Engineering quality 65scored by claude-code/claude-opus-5-5 (quality-3 rubric)prompt 91fe8ca4ac946f0f
How this score was reached…
Open the pageDetails

claude-opus-5-5effort: high

Anthropic · 82 / 100 · Quality v3 · 8/8 pages · 3h 29m · $36.60

Screenshot of the page claude-opus-5-5 made for Aero Lab89
Aero Lab claude-opus-5-5 · effort: high 44m 00s · 261k tokens · $6.50 Quality v3 · Brief delivered 95 · Working behaviour 100 · Look and feel 81 · Engineering quality 66scored by claude-code/claude-opus-5-5 (quality-3 rubric)prompt 3ef604ea3997fb42
Earlier evaluations

7.6/10 · engineering-1 · claude-code/claude-opus-5-5 (engineering-1 rubric)

7.7/10 · Quality v1 · claude-code/claude-opus-5-5 (quality-1 rubric)

Different rubrics; these values are historical, not a score change.

How this score was reached…
Open the pageDetails
Screenshot of the page claude-opus-5-5 made for Jet Odyssey79
Jet Odyssey claude-opus-5-5 · effort: high 28m 34s · 175k tokens · $5.50 Quality v3 · Brief delivered 89 · Working behaviour 100 · Look and feel 66 · Engineering quality 46scored by claude-code/claude-opus-5-5 (quality-3 rubric)prompt 14bd7252a809672d
Earlier evaluations

7.0/10 · Quality v1 · claude-code/claude-opus-5-5 (quality-1 rubric)

6.8/10 · engineering-1 · claude-code/claude-opus-5-5 (engineering-1 rubric)

Different rubrics; these values are historical, not a score change.

How this score was reached…
Open the pageDetails
Screenshot of the page claude-opus-5-5 made for Blast Island84
Blast Island claude-opus-5-5 · effort: high 37m 24s · 239k tokens · $6.01 Quality v3 · Brief delivered 92 · Working behaviour 100 · Look and feel 75 · Engineering quality 58scored by claude-code/claude-opus-5-5 (quality-3 rubric)prompt a282381696456fc9
Earlier evaluations

7.5/10 · Quality v1 · claude-code/claude-opus-5-5 (quality-1 rubric)

7.2/10 · engineering-1 · claude-code/claude-opus-5-5 (engineering-1 rubric)

Different rubrics; these values are historical, not a score change.

How this score was reached…
Open the pageDetails
Screenshot of the page claude-opus-5-5 made for Launch Day79
Launch Day claude-opus-5-5 · effort: high 38m 57s · 242k tokens · $7.20 Quality v3 · Brief delivered 86 · Working behaviour 100 · Look and feel 64 · Engineering quality 68scored by claude-code/claude-opus-5-5 (quality-3 rubric)prompt 155b76cde8ba1880
Earlier evaluations

6.7/10 · engineering-1 · claude-code/claude-opus-5-5 (engineering-1 rubric)

7.7/10 · Quality v1 · claude-code/claude-opus-5-5 (quality-1 rubric)

Different rubrics; these values are historical, not a score change.

How this score was reached…
Open the pageDetails
Screenshot of the page claude-opus-5-5 made for Alex Optics66
Alex Optics claude-opus-5-5 · effort: high 23m 51s · 143k tokens · $4.24 Quality v3 · Brief delivered 80 · Working behaviour 76 · Look and feel 60 · Engineering quality 58scored by claude-code/claude-opus-5-5 (quality-3 rubric)prompt e519ec9dadc0a186
Earlier evaluations

6.0/10 · Quality v1 · claude-code/claude-opus-5-5 (quality-1 rubric)

5.6/10 · engineering-1 · claude-code/claude-sonnet-5-5 (engineering-1 rubric)

Different rubrics; these values are historical, not a score change.

How this score was reached…
Open the pageDetails
Screenshot of the page claude-opus-5-5 made for Afterburner86
Afterburner claude-opus-5-5 · effort: high 15m 38s · 101k tokens · $2.85 Quality v3 · Brief delivered 97 · Working behaviour 100 · Look and feel 72 · Engineering quality 59scored by claude-code/claude-opus-5-5 (quality-3 rubric)prompt e4ab4889f06802b1
Earlier evaluations

8.3/10 · Quality v1 · claude-code/claude-opus-5-5 (quality-1 rubric)

8.5/10 · engineering-1 · claude-code/claude-opus-5-5 (engineering-1 rubric)

Different rubrics; these values are historical, not a score change.

How this score was reached…
Open the pageDetails
Screenshot of the page claude-opus-5-5 made for Hangar Ops89
Hangar Ops claude-opus-5-5 · effort: high 1m 21s · 10k tokens · $0.34 Quality v3 · Brief delivered 97 · Working behaviour 96 · Look and feel 75 · Engineering quality 83Fixed 9 of 10 bugs · 8 of 8 features still work · 86 lines changedscored by claude-code/claude-opus-5-5 (quality-3 rubric)prompt 86adb1d1b1c125c3
Earlier evaluations

8.6/10 · engineering-1 · claude-code/claude-opus-5-5 (engineering-1 rubric)

7.4/10 · Quality v1 · claude-code/claude-opus-5-5 (quality-1 rubric)

Different rubrics; these values are historical, not a score change.

How this score was reached…
Open the pageDetails
Screenshot of the page claude-opus-5-5 made for Rotor Rampage81
Rotor Rampage claude-opus-5-5 · effort: high 19m 41s · 124k tokens · $3.96 Quality v3 · Brief delivered 84 · Working behaviour 100 · Look and feel 76 · Engineering quality 62scored by claude-code/claude-opus-5-5 (quality-3 rubric)prompt 2db3f721e5dfca4a
Earlier evaluations

7.9/10 · Quality v1 · claude-code/claude-opus-5-5 (quality-1 rubric)

7.5/10 · engineering-1 · claude-code/claude-opus-5-5 (engineering-1 rubric)

Different rubrics; these values are historical, not a score change.

How this score was reached…
Open the pageDetails

gpt-6-astraeffort: high

OpenAI · 81 / 100 · Quality v3 · 8/8 pages · 3h 31m · ≈$31.69

Screenshot of the page gpt-6-astra made for Aero Lab83
Aero Lab gpt-6-astra · effort: high 24m 35s · 36k tokens · ≈$4.30 Quality v3 · Brief delivered 94 · Working behaviour 100 · Look and feel 69 · Engineering quality 54scored by claude-code/claude-opus-5-5 (quality-3 rubric)prompt 1e8e809e8caeb2ba
Earlier evaluations

6.0/10 · engineering-1 · claude-code/claude-opus-5-5 (engineering-1 rubric)

7.8/10 · Quality v1 · claude-code/claude-opus-5-5 (quality-1 rubric)

Different rubrics; these values are historical, not a score change.

How this score was reached…
Open the pageDetails
Screenshot of the page gpt-6-astra made for Jet Odyssey82
Jet Odyssey gpt-6-astra · effort: high 32m 29s · 48k tokens · ≈$6.16 Quality v3 · Brief delivered 93 · Working behaviour 100 · Look and feel 69 · Engineering quality 46scored by claude-code/claude-opus-5-5 (quality-3 rubric)prompt eaf6eace42027b11
Earlier evaluations

6.6/10 · engineering-1 · claude-code/claude-opus-5-5 (engineering-1 rubric)

7.6/10 · Quality v1 · claude-code/claude-opus-5-5 (quality-1 rubric)

Different rubrics; these values are historical, not a score change.

How this score was reached…
Open the pageDetails
Screenshot of the page gpt-6-astra made for Blast Island80
Blast Island gpt-6-astra · effort: high 23m 42s · 35k tokens · ≈$4.04 Quality v3 · Brief delivered 89 · Working behaviour 100 · Look and feel 68 · Engineering quality 50scored by claude-code/claude-opus-5-5 (quality-3 rubric)prompt 28ba22cd0f56ca1e
Earlier evaluations

6.7/10 · engineering-1 · claude-code/claude-opus-5-5 (engineering-1 rubric)

7.0/10 · Quality v1 · claude-code/claude-opus-5-5 (quality-1 rubric)

Different rubrics; these values are historical, not a score change.

How this score was reached…
Open the pageDetails
Screenshot of the page gpt-6-astra made for Launch Day69
Launch Day gpt-6-astra · effort: high 38m 12s · 56k tokens · ≈$7.01 Quality v3 · Brief delivered 81 · Working behaviour 98 · Look and feel 53 · Engineering quality 39scored by claude-code/claude-opus-5-5 (quality-3 rubric)prompt d1e76d48a7ac8eb6
Earlier evaluations

7.1/10 · Quality v1 · claude-code/claude-opus-5-5 (quality-1 rubric)

5.8/10 · engineering-1 · claude-code/claude-opus-5-5 (engineering-1 rubric)

Different rubrics; these values are historical, not a score change.

How this score was reached…
Open the pageDetails
Screenshot of the page gpt-6-astra made for Alex Optics85
Alex Optics gpt-6-astra · effort: high 23m 34s · 35k tokens · ≈$2.33 Quality v3 · Brief delivered 98 · Working behaviour 100 · Look and feel 70 · Engineering quality 51scored by claude-code/claude-opus-5-5 (quality-3 rubric)prompt de7c304e41dd3505
Earlier evaluations

7.5/10 · engineering-1 · claude-code/claude-opus-5-5 (engineering-1 rubric)

7.8/10 · Quality v1 · claude-code/claude-opus-5-5 (quality-1 rubric)

Different rubrics; these values are historical, not a score change.

How this score was reached…
Open the pageDetails
Screenshot of the page gpt-6-astra made for Afterburner81
Afterburner gpt-6-astra · effort: high 29m 39s · 34k tokens · ≈$2.39 Quality v3 · Brief delivered 98 · Working behaviour 100 · Look and feel 61 · Engineering quality 43scored by claude-code/claude-opus-5-5 (quality-3 rubric)prompt e08d0617005c33f9
Earlier evaluations

8.2/10 · engineering-1 · claude-code/claude-opus-5-5 (engineering-1 rubric)

7.8/10 · Quality v1 · claude-code/claude-opus-5-5 (quality-1 rubric)

Different rubrics; these values are historical, not a score change.

How this score was reached…
Open the pageDetails
Screenshot of the page gpt-6-astra made for Hangar Planner89
Hangar Planner gpt-6-astra · effort: high 8m 07s · 23k tokens · ≈$1.65 Quality v3 · Brief delivered 99 · Working behaviour 96 · Look and feel 79 · Engineering quality 70Fixed 16 of 16 bugs · 14 of 14 features still work · 545 lines changedscored by claude-code/claude-opus-5-5 (quality-3 rubric)prompt 14deca81c8b3a6c9
Earlier evaluations

7.3/10 · Quality v1 · claude-code/claude-opus-5-5 (quality-1 rubric)

9.0/10 · engineering-1 · claude-code/claude-opus-5-5 (engineering-1 rubric)

Different rubrics; these values are historical, not a score change.

How this score was reached…
Open the pageDetails
Screenshot of the page gpt-6-astra made for Rotor Rampage79
Rotor Rampage gpt-6-astra · effort: high 22m 30s · 33k tokens · ≈$2.28 Quality v3 · Brief delivered 86 · Working behaviour 100 · Look and feel 73 · Engineering quality 50scored by claude-code/claude-opus-5-5 (quality-3 rubric)prompt d196c18e5127f818
Earlier evaluations

7.2/10 · engineering-1 · claude-code/claude-opus-5-5 (engineering-1 rubric)

7.8/10 · Quality v1 · claude-code/claude-opus-5-5 (quality-1 rubric)

Different rubrics; these values are historical, not a score change.

How this score was reached…
Open the pageDetails
Screenshot of the page gpt-6-astra made for Unzip the Desert85
Unzip the Desertwildcard gpt-6-astra · effort: high 8m 53s · 24k tokens · ≈$1.55 Quality v3 · Brief delivered 98 · Working behaviour 100 · Look and feel 70 · Engineering quality 54scored by claude-code/claude-opus-5-5 (quality-3 rubric)prompt 8a3d9f5098d4145f
Earlier evaluations

6.9/10 · engineering-1 · claude-code/claude-opus-5-5 (engineering-1 rubric)

7.4/10 · Quality v1 · claude-code/claude-opus-5-5 (quality-1 rubric)

Different rubrics; these values are historical, not a score change.

How this score was reached…
Open the pageDetails