Skip to main content

Model comparison

Claude 3 Haiku vs Claude Fable 5

Data verified

Head-to-head evidence from 11 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

21.39/100
Margin
62.3pts
winning →
83.68/100
0 category wins0 category wins

Public leaderboard positions: Claude 3 Haiku #194 (Supported); Claude Fable 5 #2 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Claude 3 Haiku and Claude Fable 5 share 11 comparable benchmark results. 0 of 8 categories are comparable. 1 result is unique to Claude 3 Haiku; 23 to Claude Fable 5.

Updated July 23, 2026
Shared results
11
Claude 3 Haiku only
1
Claude Fable 5 only
23
Comparable categories
0 / 8

Benchmark data for Claude 3 Haiku and Claude Fable 5 is coming soon on BenchLM.

Confidence note. This is a partial-evidence comparison with 11 shared benchmark results across 5 evidence categories; 0 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

BenchLM has partial data for these models, but not enough overlapping benchmark coverage to produce a fair score-level comparison yet.

Claude Fable 5 is priced at $10.00 input / $50.00 output per 1M tokens, versus $0.25 input / $1.25 output per 1M tokens for Claude 3 Haiku. Claude Fable 5 has the larger context window at 1M+, compared with 200K for Claude 3 Haiku.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Category scores and score margins for Claude 3 Haiku and Claude Fable 5
CategoryClaude 3 HaikuΔClaude Fable 5
AgenticClaude 3 HaikuNot measuredMarginNo overlapClaude Fable 584.6
CodingClaude 3 HaikuNot measuredMarginNo overlapClaude Fable 589.2
MultimodalClaude 3 HaikuNot measuredMarginNo overlapClaude Fable 557.9

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricClaude 3 HaikuClaude Fable 5Comparison
Input / output priceUSD per 1M tokensClaude 3 Haiku$0.25 input / $1.25 outputClaude Fable 5$10 input / $50 outputClaude 3 Haiku has the lower combined listed price.
Generation speedtokens per secondClaude 3 Haiku138 tok/sClaude Fable 5Not availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenClaude 3 Haiku1.16 sClaude Fable 5Not availableA complete latency comparison is not available.
Context windowmaximum listed tokensClaude 3 Haiku200KClaude Fable 51M+Claude Fable 5 lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkClaude 3 HaikuClaude Fable 5Result
τ²-bench resultsSource 21.1%98.5%Claude Fable 5 leads
Terminal-Bench 2.0Source 84.3%Not comparable
OSWorld-VerifiedSource 85%Not comparable
GDPval-AASource 1748Not comparable
AA Agentic IndexSource 52.8%Not comparable
GDPval-AASource 62.4%Not comparable
AA BriefcaseSource 1574Not comparable
AA AutomationBenchSource 48.6%Not comparable
AA EnterpriseOps-GymSource 51.1%Not comparable
AA Harvey LABSource 93.6%Not comparable
AA Tau3 BankingSource 26.8%Not comparable
terminalBenchHardSource 62.9%Not comparable
aaTerminalBench21Source 84.6%Not comparable
Coding
BenchmarkClaude 3 HaikuClaude Fable 5Result
AA-SciCodeSource 18.6%60.2%Claude Fable 5 leads
SWE-bench VerifiedSource 95%Not comparable
SWE-bench ProSource 80%Not comparable
FrontierCode 1.1 MainSource 53.5%Not comparable
Terminal-Bench 2.0Source 84.3%Not comparable
cursorBench31Source 70.6%Not comparable
cursorBench32Source 70.5%Not comparable
VulcanBench v3Source 87.0%Not comparable
AA Coding IndexSource 76.5%Not comparable
Reasoning
BenchmarkClaude 3 HaikuClaude Fable 5Result
AA-LCRSource 21.0%70.0%Claude Fable 5 leads
CritPtSource 0.0%28.6%Claude Fable 5 leads
Knowledge
BenchmarkClaude 3 HaikuClaude Fable 5Result
Artificial Analysis Intelligence IndexSource 3.9%59.9%Claude Fable 5 leads
AA-GPQA DiamondSource 37.4%92.6%Claude Fable 5 leads
AA-HLESource 3.9%53.3%Claude Fable 5 leads
AA-Omniscience IndexSource -47.6%40.2%Claude Fable 5 leads
AA-Omniscience AccuracySource 17.2%61.4%Claude Fable 5 leads
AA-Omniscience Hallucination RateSource 78.2%54.9%Claude Fable 5 leads
Multimodal
BenchmarkClaude 3 HaikuClaude Fable 5Result
AA-MMMU-ProSource 30.8%Not comparable
Blueprint-Bench 2Source 38.6%Not comparable
OfficeQA ProSource 57.9%Not comparable
Design Arena WebsiteSource 1332Not comparable
Inst. Following
BenchmarkClaude 3 HaikuClaude Fable 5Result
AA-IFBenchSource 36.1%63.5%Claude Fable 5 leads
Frequently Asked Questions (3)

Can I compare Claude 3 Haiku and Claude Fable 5 on BenchLM yet?

Not fully yet. BenchLM is tracking both models, but the sourced benchmark breakdown for this comparison is still coming soon.

Why does this comparison show “coming soon”?

BenchLM only shows category winners and benchmark-level calls when we have sourced results that can be compared fairly. For these models, the public benchmark coverage is not complete enough yet.

What data is available for Claude 3 Haiku and Claude Fable 5 today?

Claude 3 Haiku: $0.25 input / $1.25 output per 1M tokens Claude Fable 5: $10.00 input / $50.00 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.

Related Comparisons

Last updated: July 23, 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.