Skip to main content
ModelScale

Claude Haiku 4.5

Anthropic · Proprietary · rank 102 · bench-align-v5

Canonical idclaude-haiku-4-5
Overall score52.91
Context window200K tokens
Release date2025-10-15
Access typeProprietary
Blended $/1M$2.0075% input / 25% output

Capability shape

Seven axes from the ranking source. A missing axis is drawn as a gap.

Capability evidence

AgenticUnavailable
Coding30.6
Knowledge53.6
ReasoningUnavailable
Multimodal & GroundedUnavailable
Instruction FollowingUnavailable
Math28.9

Runtime service evidence

Measured values with the date they were observed. Nothing is inferred from a sibling model or a provider claim.

Time to first token: latency to the first answer chunk (Artificial Analysis, via BenchLM). Reasoning models include thinking time, so values can run to tens or hundreds of seconds.

Evidence key: ObservedUnavailable

Runtime measurements
MeasurementValueObservedLast goodEvidence
Time to first tokenUnavailableUnavailableUnavailable
ThroughputUnavailableUnavailableUnavailable

Regional or per-endpoint measurements appear only when the API supplies them; none are modelled here.

Endpoint and price matrix

Every published price component, including cache reads and writes.

Price components
ComponentUSDEvidence
Input / 1M tokens$1.00
Output / 1M tokens$5.00
Cache read / 1M tokens$0.10
Cache write / 1M tokensUnavailable
Blended / 1M (75% input / 25% output)$2.00
Self-hosted listingAnthropic official public pricing for Claude Haiku 4.5 as referenced by Anthropic's April 2026 model pages.The rates above are a hosted price matched from another provider, not a first-party list price.

Workload-aware monthly cost example

10 conversations per day × 8 messages × 22 active days, 1200 input and 400 output tokens per message, no cache. This uses the same calculator as the cost simulator, so an unavailable applicable rate makes the example unavailable too.

Modelled monthly cost$5.63
Modelled tokens2.82M
Open the simulatorChange this workload

Benchmark record

11 matched benchmark rows with their published value, unit, and provenance.

Knowledge

Knowledge benchmarks
BenchmarkValueTasksDifficultyProvenance
GPQA Diamond (Vals)
GPQA Diamond, Vals AI run
72.2Graduate-level science questionsExpert reasoningVals AI GPQA Diamond, Vals AI run leaderboard
MMLU-Pro (Vals)
MMLU-Pro, Vals AI run
78.7Academic multiple-choice questionsBroad academic knowledgeVals AI MMLU-Pro, Vals AI run leaderboard

Coding

Coding benchmarks
BenchmarkValueTasksDifficultyProvenance
SWE-bench Verified
Software Engineering Benchmark Verified
73.3500 verified issuesProfessional software engineeringSWE-bench: Can Language Models Resolve Real-World GitHub Issues?
VulcanBench v3
VulcanBench v3
76.223 post-cutoff repository tasks in the v3 reportProfessional multi-file software engineeringVulcanBench
LiveCodeBench (Vals)
LiveCodeBench, Vals AI run
41.2Competitive programming problems (easy, medium, hard)Frontier codingVals AI LiveCodeBench, Vals AI run leaderboard
SWE-bench (Vals)
SWE-bench, Vals AI run
66.6Real repository issues by human time bucketFrontier coding agentsVals AI SWE-bench, Vals AI run leaderboard

Mathematics

Mathematics benchmarks
BenchmarkValueTasksDifficultyProvenance
FrontierMath v2 (Tiers 1-3)
FrontierMath v2 Tiers 1-3
5.903295 private advanced mathematics problemsFrom olympiad-plus to early research mathematicsFrontierMath v2 benchmark hub
FrontierMath v2 (Tier 4)
FrontierMath v2 Tier 4
2.08343 private extreme-difficulty mathematics problemsResearch-level mathematics requiring hours or days of expert workFrontierMath Tier 4 v2 leaderboard

Agentic

Agentic benchmarks
BenchmarkValueTasksDifficultyProvenance
JobBench
JobBench
16.0130 tasks across 35 occupationsProfessional multi-source workflowsJobBench: Aligning Agent Work With Human Will
Terminal-Bench 2.1 (Vals)
Terminal-Bench 2.1, Vals AI run
43.8Difficult terminal tasksFrontier agenticVals AI Terminal-Bench 2.1, Vals AI run leaderboard

Multimodal & Grounded

Multimodal & Grounded benchmarks
BenchmarkValueTasksDifficultyProvenance
Design Arena Website
Design Arena Website Elo
1134Website generation comparisonsDesign and website generationOpenRouter Grok 4.3 benchmarks

Lifecycle and limitations log

Lifecycle events the source associates with this model, plus what this profile does not claim.

No lifecycle event references this model.

That is not evidence the model has no lifecycle plan — only that this source published none.

What this profile does not claimValues are reproduced exactly as their sources published them, in the units those sources declared; none are converted, interpolated, or averaged across providers. Any field marked unavailable was attempted and not returned — the attempt timestamp is in each badge. Last attempted fetch for this model’s score: 2026-09-17 17:17 UTC.