Coding
Like-for-like- Claude 3.5 Sonnet
- 49.0
- Claude Haiku 4.5
- 73.3
- Weighted basis
- 1 vs 1 rows
- Reading
- Claude Haiku 4.5 leads
Claude 3.5 Sonnet vs Claude Haiku 4.5
Updated September 3, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
Claude Haiku 4.5 has the higher public score estimate, 57.72 versus 48.68, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
3 results are shared. Category rows based on different benchmark sets are marked directional and do not name a winner.
Which one for your work
Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.
Coding work
Code generation, repair, and software-engineering tasks
Claude Haiku 4.5
Claude Haiku 4.5 leads on the same 1 weighted benchmark row.
Confidence: limited
Chat turn cost
1K fresh input + 500 output tokens
Claude Haiku 4.5
Claude Haiku 4.5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Show secondary and unsupported calls
Repository review cost
50K fresh input + 3K output tokens
Claude Haiku 4.5
Claude Haiku 4.5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
No shared weighted benchmark basis supports a winner.
Confidence: limited
Long documents
Prompts that approach the documented context limit
No clear pick
The documented context windows are equal.
Confidence: documented
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. Claude 3.5 Sonnet does not fit this workload in one request. Claude Haiku 4.5 does not fit this workload in one request. Claude 3.5 Sonnet has no published cached-input rate, so cached tokens use its listed input rate.
Confidence: rate-fallback
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
1 Claude 3.5 Sonnet only
3 Shared
2 Claude Haiku 4.5 only
- Shared results
- 3
- Claude 3.5 Sonnet only
- 1
- Claude Haiku 4.5 only
- 2
- Like-for-like categories
- 2 / 8
Category results, on a stated basis
Each row states whether both averages use the same weighted benchmark set. Directional and not-comparable rows remain visible, but they never receive a winner in this template.
Math
Like-for-like- Claude 3.5 Sonnet
- 1.6
- Claude Haiku 4.5
- 4.9
- Weighted basis
- 2 vs 2 rows
- Reading
- Claude Haiku 4.5 leads
Agentic
Not comparable- Claude 3.5 Sonnet
- Not measured
- Claude Haiku 4.5
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Reasoning
Not comparable- Claude 3.5 Sonnet
- Not measured
- Claude Haiku 4.5
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Knowledge
Not comparable- Claude 3.5 Sonnet
- 59.4
- Claude Haiku 4.5
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
Multilingual
Not comparable- Claude 3.5 Sonnet
- Not measured
- Claude Haiku 4.5
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Multimodal
Not comparable- Claude 3.5 Sonnet
- Not measured
- Claude Haiku 4.5
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Instruction following
Not comparable- Claude 3.5 Sonnet
- Not measured
- Claude Haiku 4.5
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
| Category | Claude 3.5 Sonnet | Claude Haiku 4.5 | Weighted basis | Reading |
|---|---|---|---|---|
| Coding | 49.0 | 73.3 | Like-for-like1 vs 1 rows | Claude Haiku 4.5 leads |
| Math | 1.6 | 4.9 | Like-for-like2 vs 2 rows | Claude Haiku 4.5 leads |
| Agentic | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Reasoning | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Knowledge | 59.4 | Not measured | Not comparable1 vs 0 rows | Not comparable |
| Multilingual | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Multimodal | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Instruction following | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
Shape of the matched evidence
Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.
Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.
SWE-bench Verified
Coding
Claude 3.5 Sonnet: 49%Claude Haiku 4.5: 73.3%Normalized gap 24.3Claude 3.5 Sonnet source Claude Haiku 4.5 sourceFrontierMath v2 (Tiers 1-3)
Math
FrontierMath v2 (Tier 4)
Math
What each workload costs
Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.
Chat turn
1K fresh input + 500 output tokens
- Claude 3.5 Sonnet
- $0.0105
- Fits in one request
- Claude Haiku 4.5
- $0.0035
- Fits in one request
Claude Haiku 4.5 has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- Claude 3.5 Sonnet
- $0.195
- Fits in one request
- Claude Haiku 4.5
- $0.065
- Fits in one request
Claude Haiku 4.5 has the lower modeled cost
Costs use the listed standard API rates.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Claude 3.5 Sonnet
- $0.81
- Does not fit in one request
- Cached input priced at the published list-input rate
- Claude Haiku 4.5
- $0.09
- Does not fit in one request
Claude 3.5 Sonnet does not fit this workload in one request. Claude Haiku 4.5 does not fit this workload in one request. Claude 3.5 Sonnet has no published cached-input rate, so cached tokens use its listed input rate.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationClaude 3.5 SonnetClaude Haiku 4.5
Context window
Maximum documented context; output-token limits may be lower.
Claude 3.5 Sonnet
200K
Claude Haiku 4.5
API model ID
Claude 3.5 Sonnet
Not sourced
Claude Haiku 4.5
claude-haiku-4-5-20251001
Claude API pricingCached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Claude 3.5 Sonnet
Not published
Claude Haiku 4.5
$0.1 per 1M cached input tokens
Claude API pricingDocumented inputs
Claude 3.5 Sonnet
Not sourced
Claude Haiku 4.5
Not sourced
Documented outputs
Claude 3.5 Sonnet
Not sourced
Claude Haiku 4.5
Not sourced
Provider availability
Claude 3.5 Sonnet
Not sourced
Claude Haiku 4.5
Not sourced
Reasoning profile
Claude 3.5 Sonnet
Non-Reasoning
Claude Haiku 4.5
Non-Reasoning
Weight access
Claude 3.5 Sonnet
Proprietary
Claude Haiku 4.5
Proprietary
License
Claude 3.5 Sonnet
Proprietary
Claude Haiku 4.5
Proprietary
Release date
Claude 3.5 Sonnet
2024-06-01
Claude Haiku 4.5
2025-10-15
If you already use one of these models
- Deployment change
- Both entries list Anthropic as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
- Quality signal
- Claude Haiku 4.5 has the higher public score estimate, 57.72 versus 48.68, but the 90% score intervals overlap.
- Workload cost
- Repository review: $0.195 vs $0.065. Cache-heavy agent loop: $0.81 vs $0.09.
- Context tradeoff
- Both models list 200K.
Run the same representative tasks against both endpoints before changing production traffic.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence6 rows
Agentic
JobBench
Claude 3.5 Sonnet—Claude Haiku 4.516.0%SourceNot directly comparable
Coding
Knowledge
GPQA
Claude 3.5 Sonnet59.4%SourceClaude Haiku 4.5—Not directly comparable
Math
FrontierMath v2 (Tiers 1-3)
Shared sourceClaude 3.5 Sonnet2.069%Claude Haiku 4.55.903%Claude Haiku 4.5 leads this result
FrontierMath v2 (Tier 4)
Shared sourceClaude 3.5 Sonnet0.000%Claude Haiku 4.52.083%Claude Haiku 4.5 leads this result
Frequently asked questions
Which is better, Claude 3.5 Sonnet or Claude Haiku 4.5?
Claude Haiku 4.5 has the higher public score estimate, 57.72 versus 48.68, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
Which is better for coding, Claude 3.5 Sonnet or Claude Haiku 4.5?
Claude Haiku 4.5 leads the like-for-like coding comparison across 1 shared weighted benchmark row.
Which is better for agentic tasks, Claude 3.5 Sonnet or Claude Haiku 4.5?
The published evidence does not provide a shared weighted agentic tasks basis for both models, so BenchLM does not name a agentic tasks winner.
Which costs less, Claude 3.5 Sonnet or Claude Haiku 4.5?
For the stated presets, chat costs $0.0105 on Claude 3.5 Sonnet and $0.0035 on Claude Haiku 4.5; repository review costs $0.195 and $0.065; the cache-heavy agent loop costs $0.81 and $0.09. Claude 3.5 Sonnet does not fit this workload in one request. Claude Haiku 4.5 does not fit this workload in one request. Claude 3.5 Sonnet has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, Claude 3.5 Sonnet or Claude Haiku 4.5?
Both models list the same context window, 200K.
Related comparisons
Last updated September 3, 2026
Watch Claude 3.5 Sonnet vs Claude Haiku 4.5
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.