What is the IQ of fable-5?

fable-5 has an estimated IQ of 133, which ranks #12 out of 176 public models on the AI IQ leaderboard. The score combines seven equally weighted reasoning dimensions using measured benchmark results and conservative estimates for missing coverage.

What is fable-5 best at?

Among the dimensions with published benchmark results, fable-5 ranks highest in Academic Reasoning (IQ 134, #11 of 203) and Reliability (IQ 129, #10 of 177). Its lowest-ranked measured dimension is Knowledge Work (IQ 129, #15 of 176).

What is the EQ of fable-5?

fable-5 has an estimated EQ of 128. EQ measures emotional reasoning — how well a model reads and responds to emotional context — and is scored separately from IQ.

Which benchmarks has fable-5 been tested on?

fable-5 has published results on 34 of the 39 benchmarks behind AI IQ's Composite IQ, including ARC-AGI-1, MMMU-Pro, Humanity's Last Exam, AA Omniscience and SciCode.

How much does fable-5 cost?

fable-5 costs $10.00 per million input tokens and $50.00 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $87.20 per million input-plus-output tokens.

Is fable-5 open source?

No — fable-5 is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.

Who developed fable-5?

fable-5 was developed by Anthropic, based in the United States.

When was fable-5 released?

fable-5 was publicly released on June 9, 2026.

How large is the context window of fable-5?

fable-5 supports a context window of 1,000,000 tokens — the amount of text it can consider in a single request.

In independent measurements, fable-5 generates about 69 tokens per second, with a typical response time of about 109 seconds.

AnthropicReleased Jun 9, 2026

Proprietary

fable-5

Strongest in Academic Reasoning (#11 of 203) and Reliability (#10 of 177); weakest in Knowledge Work (#15 of 176). All seven dimensions are measured.

Composite IQ ?

133

#12 of 176 ranked models · ahead of 94%

Anthropic's #5 model, behind opus-5.5 (141)

Effective cost

$87.20/1M

$10 in · $50 out

Speed

69tok/s

109s typical response

Context

1Mtokens

1,000,000 tokens in

Evidence

7of 7 dims

34 of 39 benchmarks

Compare with gpt-6.1-solAPI pricing

IQ profile

Seven dimensions, averaged equally into Composite IQ

Compare shape with

Measured95% range

#1 in dimensionTop-10 median

IQ dimensions

Ranks are among models scored in each dimension. Ranges are model-based estimates, not calibrated confidence intervals.

DimensionIQPosition · 70–160RankEvidencevs Top 10

Abstract ReasoningAbstract

122measured

#12 / 201

4/5

-4.5

Mathematical ReasoningMath

143measured

#11 / 176

4/5

-4

Academic ReasoningAcademic

134measured

#11 / 203

6/6

-1.5

Programmatic ReasoningCoding

141measured

#14 / 177

5/6

-8.5

Computer UseComputer Use

134measured

#12 / 176

4/5

-9

ReliabilityReliability

129measured

#10 / 177

5/6

-5

Knowledge WorkKnowledge Work

129measured

#15 / 176

6/6

-2.5

fable-595% range (model-based, uncalibrated)Top-10 median#1 in dimension100 = average human

Benchmark results

34 of 39 Composite IQ benchmarks have a published result for fable-5. Benchmarks without a result stay listed so gaps are visible.

Abstract Reasoning IQ 122 · measuredBest: #1 of 68 on ARC-AGI-14/5

BenchmarkScorePercentileRankLeader · source

ARC-AGI-1

Full source leaderboard reconciliation · Oct 23

98.5%

#1 / 68

Leader on this benchmark
Full source leaderboard reconciliation · Oct 23

ARC-AGI-2

Full source leaderboard reconciliation · Oct 23

89.2%

#9 / 68

Leader gpt-6-astra · 95.0%
Full source leaderboard reconciliation · Oct 23

Mystery Game Puzzles

Full source leaderboard reconciliation vEpoch 100-position leaderboard (task implementation versions recorded per run) · Oct 23

52.0%

#10 / 55

Leader gpt-6-astra · 84.0%
Full source leaderboard reconciliation vEpoch 100-position leaderboard (task implementation versions recorded per run) · Oct 23

Chess Puzzles

Epoch AI vEpoch 100-position leaderboard (task implementation versions recorded per run) · Oct 14

41.0%

#16 / 76

Leader gpt-6-astra · 72.0%
Epoch AI vEpoch 100-position leaderboard (task implementation versions recorded per run) · Oct 14

Not yet reported

ARC-AGI-3

Mathematical Reasoning IQ 143 · measuredBest: #5 of 72 on FrontierMath Tier 44/5

BenchmarkScorePercentileRankLeader · source

FrontierMath Tier 4

Full source leaderboard reconciliation · Oct 23

90.2%

#5 / 72

Leader gpt-6.1-sol · 100%
Full source leaderboard reconciliation · Oct 23

FrontierMath Tier 1-3

Full source leaderboard reconciliation · Oct 23

87.0%

#9 / 84

Leader gpt-6-astra · 93.7%
Full source leaderboard reconciliation · Oct 23

ProofBench 1.1

Full source leaderboard reconciliation v1.1 · Oct 27

95.0%

#8 / 48

Leader fable-5.1 · 100%
Full source leaderboard reconciliation v1.1 · Oct 27

MathArena

Full source leaderboard reconciliation · Oct 28

50.9%

#15 / 64

Leader gpt-6.1-sol · 84.0%
Full source leaderboard reconciliation · Oct 28

Not yet reported

AIME

Academic Reasoning IQ 134 · measuredBest: #2 of 89 on MMMU-Pro6/6

BenchmarkScorePercentileRankLeader · source

MMMU-Pro

Artificial Analysis model leaderboard · Sep 6

89.3%

#2 / 89

Leader fable-5.1 · 90.6%
Artificial Analysis model leaderboard · Sep 6

Humanity's Last Exam

Artificial Analysis v4.3.2 · Oct 27

55.5%

#4 / 167

Leader opus-5.5 · 61.4%
Artificial Analysis v4.3.2 · Oct 27

SciCode

Artificial Analysis v4.3.2 · Oct 27

61.0%

#5 / 167

Leader opus-5.5 · 66.9%
Artificial Analysis v4.3.2 · Oct 27

MMLU-Pro

TIGER-Lab MMLU-Pro leaderboard (missing rows only) · Sep 22

91.5%

#2 / 45

Leader fable-5.1 · 92.4%
TIGER-Lab MMLU-Pro leaderboard (missing rows only) · Sep 22

CritPt

Artificial Analysis v4.3.2 · Oct 27

28.6%

#11 / 159

Leader Muse Wonder Full · 32.9%
Artificial Analysis v4.3.2 · Oct 27

GPQA Diamond

Artificial Analysis v4.3.2 · Oct 27

92.6%

#23 / 147

Leader gpt-6-astra · 96.1%
Artificial Analysis v4.3.2 · Oct 27

Programmatic Reasoning IQ 141 · measuredBest: #1 of 25 on SWE-rebench5/6

BenchmarkScorePercentileRankLeader · source

SWE-rebench

Full source leaderboard reconciliation · Oct 23

64.5%

#1 / 25

Leader on this benchmark
Full source leaderboard reconciliation · Oct 23

LiveCodeBench

Vals.ai · Aug 4

89.8%

#4 / 61

Leader Fugu Ultra v1.0 · 93.2%
Vals.ai · Aug 4

Terminal-Bench 4.0

Artificial Analysis v4.3.2 · Oct 27

42.4%

#13 / 104

Leader Kimi K3.1 Pro · 67.2%
Artificial Analysis v4.3.2 · Oct 27

ProgramBench

Full source leaderboard reconciliation · Oct 23

33.0%

#8 / 61

Leader opus-5.5 · 65.0%
Full source leaderboard reconciliation · Oct 23

MirrorCode

Full source leaderboard reconciliation vML,+Private,2L · Oct 23

63.9%

#3 / 9

Leader opus-5.5 · 78.9%
Full source leaderboard reconciliation vML,+Private,2L · Oct 23

Not yet reported

IOI V2

Computer Use IQ 134 · measuredBest: #1 of 24 on OSWorld-Verified4/5

BenchmarkScorePercentileRankLeader · source

OSWorld-Verified

Full source leaderboard reconciliation · Oct 23

85.0%

#1 / 24

Leader on this benchmark
Full source leaderboard reconciliation · Oct 23

Arena.ai Agent Arena

Arena.ai Agent Arena · Oct 26

8.0

#11 / 70

Leader opus-5.5 · 20.9
Arena.ai Agent Arena · Oct 26

MCP Atlas

Full source leaderboard reconciliation · Oct 23

83.3%

#7 / 32

Leader muse-spark-1.1 · 88.1%
Full source leaderboard reconciliation · Oct 23

Agents' Last Exam

Full source leaderboard reconciliation · Oct 23

25.7%

#13 / 29

Leader opus-5.5 · 38.2%
Full source leaderboard reconciliation · Oct 23

Not yet reported

BrowseComp

Reliability IQ 129 · measuredBest: #4 of 158 on AA Omniscience5/6

BenchmarkScorePercentileRankLeader · source

AA Omniscience

Artificial Analysis v4.3.2 · Oct 27

43.3

#4 / 158

Leader opus-5.5 · 46.4
Artificial Analysis v4.3.2 · Oct 27

SimpleQA Verified

Full source leaderboard reconciliation · Oct 23

70.7%

#8 / 80

Leader Gemini 4 Argon · 76.0%
Full source leaderboard reconciliation · Oct 23

AA Long Context Reasoning v1.1

Artificial Analysis v4.3.2 · Oct 27

82.3%

#28 / 154

Leader kimi-k3 · 88.7%
Artificial Analysis v4.3.2 · Oct 27

BullshitBench v2

Full source leaderboard reconciliation · Oct 23

56.0%

#27 / 83

Leader opus-4.8 · 94.0%
Full source leaderboard reconciliation · Oct 23

IFBench

Artificial Analysis v4.3.2 · Oct 27

63.5%

#63 / 96

Leader minimax-m3 · 82.9%
Artificial Analysis v4.3.2 · Oct 27

Not yet reported

FACTS Grounding

Knowledge Work IQ 129 · measuredBest: #1 of 31 on EnterpriseOps-Gym-AA6/6

BenchmarkScorePercentileRankLeader · source

EnterpriseOps-Gym-AA

Full source leaderboard reconciliation v1117-task-strict-2026-09-29 · Oct 27

51.1%

#1 / 31

Leader on this benchmark
Full source leaderboard reconciliation v1117-task-strict-2026-09-29 · Oct 27

GDP.pdf

Artificial Analysis v4.3.2 · Oct 27

24.0%

#13 / 106

Leader Muse Wonder Full · 32.6%
Artificial Analysis v4.3.2 · Oct 27

AA-Briefcase v1.1 Elo

Artificial Analysis v4.3.2 · Oct 27

1,537

#16 / 111

Leader sonnet-5.5 · 1,812
Artificial Analysis v4.3.2 · Oct 27

GDPval-AA v2.1 normalized score

Artificial Analysis v4.3.2 · Oct 20

55.5%

#19 / 124

Leader opus-5.5 · 68.3%
Artificial Analysis v4.3.2 · Oct 20

AA-AnalystAgent

Full source leaderboard reconciliation vpass^5-2026-09-29 · Oct 27

48.8%

#11 / 35

Leader gemini-3.7-flash · 60.0%
Full source leaderboard reconciliation vpass^5-2026-09-29 · Oct 27

AutomationBench-AA

Artificial Analysis v4.3.2 · Oct 27

54.1%

#34 / 106

Leader Gemini 4 Argon · 77.5%
Artificial Analysis v4.3.2 · Oct 27

Release & availability

Release details on record for this model.

Released: Jun 9, 2026
Developer: Anthropic
Weights: ProprietaryHosted access only
Context: 1,000,000 tokens
API price: $10 in · $50 outper 1M tokens · full pricing

About this score

How much of fable-5's IQ is measured, and how the rest is estimated.

34/ 39benchmark results

7/ 7dimensions measured

0estimated

4/5Abstract

4/5Math

6/6Academic

5/6Coding

4/5Computer Use

5/6Reliability

6/6Knowledge Work

Bar height = share of benchmarks with resultsEstimatedNo score

Measured results are shown as published

Every score in the benchmark tables comes from its source unchanged. Composite IQ averages all seven dimensions equally.

How gaps are handled

Every dimension has at least one published result.

A missing result is not a zero

Benchmark versions and evaluation harnesses can differ between sources, so small gaps between models may not be meaningful.

Read the scoring methodology →

Compare fable-5

Side-by-side pages for the models it is most often weighed against.

#1 overall

gpt-6.1-sol

IQ141 8 higherEffective cost$6.30 13.8× cheaper

Anthropic #1

opus-5.5

IQ141 8 higherEffective cost$35.73 2.4× cheaper

Closest IQ

gpt-5.6-sol

IQ133 same IQEffective cost$27.47 3.2× cheaper

Most similar profile

gpt-6.1-terra

IQ136 3 higherEffective cost$5.08 17.2× cheaper

Similar price

gpt-6-astra

IQ140 7 higherEffective cost$34.22 2.5× cheaper

#3 overall

Gemini 4 Argon

IQ140 7 higher

fable-5Comparison model

Compare with any modelBrowse all comparisons →

Frequently asked questions

Quick answers about fable-5, drawn from the same data as the rest of this page.

How AI IQ scores models →Get this data from the API →

What is the IQ of fable-5?: fable-5 has an estimated IQ of 133, which ranks #12 out of 176 public models on the AI IQ leaderboard. The score combines seven equally weighted reasoning dimensions using measured benchmark results and conservative estimates for missing coverage.
What is fable-5 best at?: Among the dimensions with published benchmark results, fable-5 ranks highest in Academic Reasoning (IQ 134, #11 of 203) and Reliability (IQ 129, #10 of 177). Its lowest-ranked measured dimension is Knowledge Work (IQ 129, #15 of 176).
What is the EQ of fable-5?: fable-5 has an estimated EQ of 128. EQ measures emotional reasoning — how well a model reads and responds to emotional context — and is scored separately from IQ.
Which benchmarks has fable-5 been tested on?: fable-5 has published results on 34 of the 39 benchmarks behind AI IQ's Composite IQ, including ARC-AGI-1, MMMU-Pro, Humanity's Last Exam, AA Omniscience and SciCode.
How much does fable-5 cost?: fable-5 costs $10.00 per million input tokens and $50.00 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $87.20 per million input-plus-output tokens.
Is fable-5 open source?: No — fable-5 is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.
Who developed fable-5?: fable-5 was developed by Anthropic, based in the United States.
When was fable-5 released?: fable-5 was publicly released on June 9, 2026.
How large is the context window of fable-5?: fable-5 supports a context window of 1,000,000 tokens — the amount of text it can consider in a single request.
How fast is fable-5?: In independent measurements, fable-5 generates about 69 tokens per second, with a typical response time of about 109 seconds.