Skip to main content

Model comparison

Claude 3 Haiku vs GPT-5.2

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
37.0pts
winning →
OpenAI
58.43/100
0 category wins0 category wins

Public leaderboard positions: Claude 3 Haiku #194 (Supported); GPT-5.2 #64 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Claude 3 Haiku and GPT-5.2 share 11 comparable benchmark results. 0 of 8 categories are comparable. 1 result is unique to Claude 3 Haiku; 17 to GPT-5.2.

Updated July 20, 2026
Shared results
11
Claude 3 Haiku only
1
GPT-5.2 only
17
Comparable categories
0 / 8

Benchmark data for Claude 3 Haiku and GPT-5.2 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.

GPT-5.2 is priced at $1.75 input / $14.00 output per 1M tokens, versus $0.25 input / $1.25 output per 1M tokens for Claude 3 Haiku. GPT-5.2 has the larger context window at 400K, 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 GPT-5.2
CategoryClaude 3 HaikuΔGPT-5.2
AgenticClaude 3 HaikuNot measuredMarginNo overlapGPT-5.255.7
CodingClaude 3 HaikuNot measuredMarginNo overlapGPT-5.270.6
ReasoningClaude 3 HaikuNot measuredMarginNo overlapGPT-5.252.9
KnowledgeClaude 3 HaikuNot measuredMarginNo overlapGPT-5.292.4
MathClaude 3 HaikuNot measuredMarginNo overlapGPT-5.235.2
MultimodalClaude 3 HaikuNot measuredMarginNo overlapGPT-5.280.4

Operational comparison

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

MetricClaude 3 HaikuGPT-5.2Comparison
Input / output priceUSD per 1M tokensClaude 3 Haiku$0.25 input / $1.25 outputGPT-5.2$1.75 input / $14 outputClaude 3 Haiku has the lower combined listed price.
Generation speedtokens per secondClaude 3 Haiku138 tok/sGPT-5.273 tok/sClaude 3 Haiku has the higher measured throughput.
First-answer latencyseconds to first tokenClaude 3 Haiku1.16 sGPT-5.2130.34 sClaude 3 Haiku reaches the first token sooner.
Context windowmaximum listed tokensClaude 3 Haiku200KGPT-5.2400KGPT-5.2 lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkClaude 3 HaikuGPT-5.2Result
τ²-bench resultsSource 21.1%84.8%GPT-5.2 leads
BrowseCompSource 65.8%Not comparable
OSWorld-VerifiedSource 47.3%Not comparable
Gert LabsSource 46.54%Not comparable
JobBenchSource 34.3%Not comparable
Coding
BenchmarkClaude 3 HaikuGPT-5.2Result
AA-SciCodeSource 18.6%52.1%GPT-5.2 leads
SWE-bench VerifiedSource 80%Not comparable
SWE-bench ProSource 55.6%Not comparable
Vibe Code BenchSource 53.50%Not comparable
Reasoning
BenchmarkClaude 3 HaikuGPT-5.2Result
AA-LCRSource 21.0%72.7%GPT-5.2 leads
CritPtSource 0.0%11.6%GPT-5.2 leads
ARC-AGI-2Source 52.9%Not comparable
Knowledge
BenchmarkClaude 3 HaikuGPT-5.2Result
Artificial Analysis Intelligence IndexSource 3.9%42.2%GPT-5.2 leads
AA-GPQA DiamondSource 37.4%90.3%GPT-5.2 leads
AA-HLESource 3.9%35.4%GPT-5.2 leads
AA-Omniscience IndexSource -47.6%-1.0%GPT-5.2 leads
AA-Omniscience AccuracySource 17.2%43.8%GPT-5.2 leads
AA-Omniscience Hallucination RateSource 78.2%79.7%Claude 3 Haiku leads
GPQASource 92.4%Not comparable
Math
BenchmarkClaude 3 HaikuGPT-5.2Result
AA AIME 2025Source 99.0%Not comparable
FrontierMath v2 (Tiers 1-3)Source 40.700%Not comparable
FrontierMath v2 (Tier 4)Source 18.800%Not comparable
Multimodal
BenchmarkClaude 3 HaikuGPT-5.2Result
AA-MMMU-ProSource 30.8%Not comparable
MMMU-ProSource 79.5%Not comparable
MathVisionSource 83.0%Not comparable
CharXivSource 82.1%Not comparable
V*Source 75.9%Not comparable
Design Arena WebsiteSource 1227Not comparable
Inst. Following
BenchmarkClaude 3 HaikuGPT-5.2Result
AA-IFBenchSource 36.1%75.4%GPT-5.2 leads
Frequently Asked Questions (3)

Can I compare Claude 3 Haiku and GPT-5.2 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 GPT-5.2 today?

Claude 3 Haiku: $0.25 input / $1.25 output per 1M tokens GPT-5.2: $1.75 input / $14.00 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 20, 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.