Long documents
Prompts that approach the documented context limit
Claude Haiku 5.5
Claude Haiku 5.5 has the larger documented context window.
Confidence: documented
Claude Haiku 5.5 vs Step 3.7 Flash
Updated October 7, 2026. Rank says Claude Haiku 5.5 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
Both of these models will change. Get the price, version and retirement notices for the pair, each with its source. Follow model changes
Share or export
Decision reading
Claude Haiku 5.5 has the higher public point estimate, 66.32 versus 44.21. Their conditional score ranges overlap. These ranges do not establish rank confidence. 1 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
- Shared results
- 1
- Claude Haiku 5.5 only
- 4
- Step 3.7 Flash only
- 10
- Like-for-like categories
- 0 / 8
Estimated: Claude Haiku 5.5 and Step 3.7 Flash. Conditional ranges do not establish rank confidence.How the comparison works
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.
Chat turn cost
1K fresh input + 500 output tokens
Claude Haiku 5.5
Claude Haiku 5.5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-ratesCache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Claude Haiku 5.5
Claude Haiku 5.5 has the lower estimated token cost for this stated workload. Step 3.7 Flash has no published cached-input rate, so cached tokens use its listed input rate.
Confidence: rate-fallback
Show secondary and unsupported calls
Repository review cost
50K fresh input + 3K output tokens
Claude Haiku 5.5
Claude Haiku 5.5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-ratesCoding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
Step 3.7 Flash is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.
Confidence: limitedAgentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
Step 3.7 Flash is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.
Confidence: limited
Which one for a specific job
Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.
The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.
60.9Claude Haiku 5.532.2Step 3.7 Flash
Directional only · BenchAlign v5.8
Claude Haiku 5.5 has the higher coding point estimate. Conditional score ranges do not establish rank confidence.
Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.
Same basis rules as the category table below
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
4 Claude Haiku 5.5 only
1 Shared
10 Step 3.7 Flash only
2 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
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.
A shared-evidence shape is not available.
BenchLM does not draw a radar or infer missing axes when the matched evidence is too sparse.
Category results, on a stated basis
Each row shows the public-lane category score for both models: the BenchAlign v5.8 lane for agentic, coding, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.
Agentic
Directional only- Claude Haiku 5.5
- 62.1
- Supported · #18/122
- Step 3.7 Flash
- 36.0
- Estimated · #71/122
- Basis
- BenchAlign v5.8 lane · 2 vs 7 public rows
- Reading
- Directional only
Coding
Directional only- Claude Haiku 5.5
- 60.9
- Supported · #20/146
- Step 3.7 Flash
- 32.2
- Estimated · #90/146
- Basis
- BenchAlign v5.8 lane · 1 vs 2 public rows
- Reading
- Directional only
Reasoning
Not comparable- Claude Haiku 5.5
- 79.2
- Unranked · 2 rankable rows
- Step 3.7 Flash
- 73.0
- Unranked · 2 rankable rows
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- Claude Haiku 5.5
- Not ranked
- Step 3.7 Flash
- 72.0
- Unranked · 3 rankable rows
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Knowledge
Not comparable- Claude Haiku 5.5
- Not ranked
- Step 3.7 Flash
- 43.9
- Estimated · #89/174
- Basis
- BenchAlign v5.8 lane · 1 vs 0 public rows
- Reading
- Not comparable
Multilingual
Not comparable- Claude Haiku 5.5
- Not ranked
- Step 3.7 Flash
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- Claude Haiku 5.5
- Not ranked
- Step 3.7 Flash
- 80.6
- #53/125
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- Claude Haiku 5.5
- Not ranked
- Step 3.7 Flash
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | Claude Haiku 5.5 | Step 3.7 Flash | Basis | Reading |
|---|---|---|---|---|
| Agentic | 62.1Supported · #18/122 | 36.0Estimated · #71/122 | Directional onlyBenchAlign v5.8 lane · 2 vs 7 public rows | Directional only |
| Coding | 60.9Supported · #20/146 | 32.2Estimated · #90/146 | Directional onlyBenchAlign v5.8 lane · 1 vs 2 public rows | Directional only |
| Reasoning | 79.2Unranked · 2 rankable rows | 73.0Unranked · 2 rankable rows | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multimodal | Not ranked | 72.0Unranked · 3 rankable rows | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Knowledge | Not ranked | 43.9Estimated · #89/174 | Not comparableBenchAlign v5.8 lane · 1 vs 0 public rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Instruction following | Not ranked | 80.6#53/125 | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign v5.8) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.
Supported evidence per lane · bars run 0–100Methodology
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 Haiku 5.5
- $0.00035
- Fits in one request
- Step 3.7 Flash
- $0.00077
- Fits in one request
Claude Haiku 5.5 has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- Claude Haiku 5.5
- $0.0065
- Fits in one request
- Step 3.7 Flash
- $0.01345
- Fits in one request
Claude Haiku 5.5 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 Haiku 5.5
- $0.009
- Fits in one request
- Step 3.7 Flash
- $0.0555
- Fits in one request
- Cached input priced at the published list-input rate
Claude Haiku 5.5 has the lower modeled cost
Step 3.7 Flash has no published cached-input rate, so cached tokens use its listed input rate.
Cached input falls back to the list input rate only where a cached rate is unpublished
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationClaude Haiku 5.5Step 3.7 Flash
Context window
Maximum documented context; output-token limits may be lower.
Claude Haiku 5.5
Step 3.7 Flash
256K
API model ID
Claude Haiku 5.5
claude-haiku-5-5
Anthropic Claude Haiku 5.5 model documentationStep 3.7 Flash
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Claude Haiku 5.5
$0.01 per 1M cached input tokens
Claude API pricingStep 3.7 Flash
Not published
Documented inputs
Claude Haiku 5.5
Step 3.7 Flash
Not sourced
Documented outputs
Claude Haiku 5.5
Step 3.7 Flash
Not sourced
Provider availability
Claude Haiku 5.5
Generally Available · Claude API, Amazon Bedrock, Google Cloud, Microsoft Foundry, Claude Platform on AWS
Anthropic Claude Haiku 5.5 model documentationStep 3.7 Flash
Not sourced
Reasoning profile
Claude Haiku 5.5
Reasoning
Step 3.7 Flash
Reasoning
Weight access
Claude Haiku 5.5
Proprietary
Step 3.7 Flash
Open Weight
License
Claude Haiku 5.5
Proprietary
Step 3.7 Flash
Open Weight
Release date
Claude Haiku 5.5
2026-10-07
Step 3.7 Flash
2026-05-29
If you already use one of these models
- Deployment change
- The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
- Quality signal
- Claude Haiku 5.5 has the higher public point estimate, 66.32 versus 44.21. Their conditional score ranges overlap. These ranges do not establish rank confidence.
- Workload cost
- Repository review: $0.0065 vs $0.01345. Cache-heavy agent loop: $0.009 vs $0.0555.
- Context tradeoff
- Claude Haiku 5.5 has the larger documented window (1M).
Run the same representative tasks against both endpoints before changing production traffic.
Questions
Which is better, Claude Haiku 5.5 or Step 3.7 Flash?
Claude Haiku 5.5 has the higher public point estimate, 66.32 versus 44.21. Their conditional score ranges overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.
Which is better for coding, Claude Haiku 5.5 or Step 3.7 Flash?
Claude Haiku 5.5 scores higher for coding on the public lane, 60.9 to 32.2. Step 3.7 Flash is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like. BenchLM does not name a winner for coding from a directional reading; read the shared benchmark rows directly and test the models on the same task set.
Which is better for agentic tasks, Claude Haiku 5.5 or Step 3.7 Flash?
Claude Haiku 5.5 scores higher for agentic tasks on the public lane, 62.1 to 36. Step 3.7 Flash is scored on Estimated evidence for agentic tasks, so the reading is directional rather than like-for-like. BenchLM does not name a winner for agentic tasks from a directional reading; read the shared benchmark rows directly and test the models on the same task set.
Which costs less, Claude Haiku 5.5 or Step 3.7 Flash?
For the stated presets, chat costs $0.00035 on Claude Haiku 5.5 and $0.00077 on Step 3.7 Flash; repository review costs $0.0065 and $0.01345; the cache-heavy agent loop costs $0.009 and $0.0555. Step 3.7 Flash has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, Claude Haiku 5.5 or Step 3.7 Flash?
Claude Haiku 5.5 has the larger documented context window: 1M, compared with 256K.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence15 rows
Agentic
Terminal-Bench 4.0
Claude Haiku 5.539.20%SourceStep 3.7 Flash—Not directly comparable
HLE w/ tools
Claude Haiku 5.557.4%SourceStep 3.7 Flash47.2%SourceClaude Haiku 5.5 leads this result
Terminal-Bench 2.1
Claude Haiku 5.5—Step 3.7 Flash59.5%SourceNot directly comparable
BrowseComp
Claude Haiku 5.5—Step 3.7 Flash75.8%SourceNot directly comparable
DeepSearchQA
Claude Haiku 5.5—Step 3.7 Flash92.8%SourceNot directly comparable
Toolathlon
Claude Haiku 5.5—Step 3.7 Flash49.5%SourceNot directly comparable
Claw-Eval
Claude Haiku 5.5—Step 3.7 Flash67.1%SourceNot directly comparable
Gert Labs
Claude Haiku 5.5—Step 3.7 Flash51.57%SourceNot directly comparable
Coding
Multimodal
Knowledge
HLE w/o tools
Claude Haiku 5.545.9%SourceStep 3.7 Flash—Not directly comparable
15 public results · 1 shared
Watch Claude Haiku 5.5 vs Step 3.7 Flash
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 5,500+ readers.
Last updated October 7, 2026