claude-haiku-5-5
Checking current pricing…
Chat comparison
claude-haiku-5-5vsllama-4-maverick
Compare the things that matter before you build: current price, capabilities, and latest aggregated LLM7 statistics.
Current pricing
See the cost difference clearly
llama-4-maverick
Checking current pricing…
What's different
Only capabilities that differ between these models are listed. Green highlights the broader supported option or larger context window.
Context window
claude-haiku-5-5
1,000,000 tokens
llama-4-maverickBetter fit
1,048,576 tokens
JSON mode
claude-haiku-5-5Better fit
Supported
llama-4-maverick
Not supported
Reasoning
claude-haiku-5-5Better fit
Supported
llama-4-maverick
Not supported
Capability scores
AI-estimated ratings on 30 criteria from head-to-head comparisons against 86 other text models in the LLM7 catalog, judged by TypeSafe Jev from public information (2026-10-20). Each score is the win rate against the field, relative to the strongest model for that criterion (100%). Not a benchmark.
Below 50%50–79%80–94%95%+
claude-haiku-5-5 · leads in 28
68%
Moderate
llama-4-maverick · leads in 2
40%
Weak
Knowledge & reasoning
General knowledge
claude-haiku-5-5Leads61%llama-4-maverick60%Logical reasoning
claude-haiku-5-5Leads65%llama-4-maverick26%Mathematics
claude-haiku-5-5Leads60%llama-4-maverick36%Scientific and technical depth
claude-haiku-5-5Leads55%llama-4-maverick45%Planning and task decomposition
claude-haiku-5-5Leads67%llama-4-maverick25%
Coding & tools
Code generation
claude-haiku-5-5Leads56%llama-4-maverick36%Debugging and code review
claude-haiku-5-5Leads64%llama-4-maverick33%Agentic coding
claude-haiku-5-5Leads70%llama-4-maverick34%Tool and function calling
claude-haiku-5-5Leads71%llama-4-maverick36%SQL and query writing
claude-haiku-5-5Leads64%llama-4-maverick34%
Writing & language
Creative writing
claude-haiku-5-5Leads63%llama-4-maverick48%Professional writing
claude-haiku-5-5Leads72%llama-4-maverick39%Conversational quality
claude-haiku-5-5Leads71%llama-4-maverick38%Multilingual ability
claude-haiku-5-558%llama-4-maverickLeads62%Translation
claude-haiku-5-5Leads66%llama-4-maverick47%Summarization
claude-haiku-5-5Leads72%llama-4-maverick57%
Data & professional work
Data analysis
claude-haiku-5-5Leads68%llama-4-maverick38%Professional domains
claude-haiku-5-5Leads66%llama-4-maverick41%Information extraction
claude-haiku-5-5Leads72%llama-4-maverick27%Classification and labeling
claude-haiku-5-5Leads73%llama-4-maverick49%Long-context handling
claude-haiku-5-583%llama-4-maverickLeads89%
Reliability & control
Instruction following
claude-haiku-5-5Leads71%llama-4-maverick19%Structured output
claude-haiku-5-5Leads79%llama-4-maverick7%Factual accuracy
claude-haiku-5-5Leads76%llama-4-maverick44%Safety and alignment
claude-haiku-5-5Leads76%llama-4-maverick41%Steerability
claude-haiku-5-5Leads75%llama-4-maverick31%Output consistency
claude-haiku-5-5Leads83%llama-4-maverick41%
Speed, cost & vision
Response speed
claude-haiku-5-5Leads76%llama-4-maverick45%Cost efficiency
claude-haiku-5-5Leads68%llama-4-maverick46%Image understanding
claude-haiku-5-5Leads38%llama-4-maverick25%
Latest LLM7 statistics
Recent aggregated percentages and response-time metrics from LLM7, not a global model benchmark or traffic disclosure.
Recent stability
claude-haiku-5-5
98.04%
llama-4-maverick
95.34%
Average response time
claude-haiku-5-5
18,800.08 ms
llama-4-maverick
4,496.14 ms
P95 API latency
claude-haiku-5-5
60,000 ms
llama-4-maverick
10,000 ms
Side-by-side trends
Shared charts make the observed differences easier to read. Metrics without enough history stay hidden.
Request success rate
Both models on the same scale
claude-haiku-5-5: 100%llama-4-maverick: 100%
Average API latency
Both models on the same scale
claude-haiku-5-5: 4,407 msllama-4-maverick: 4,572 ms
P95 API latency
Both models on the same scale
claude-haiku-5-5: 10,000 msllama-4-maverick: 5,000 ms
Estimate your workload
Published rates are loaded from the pricing API; per-request quotes are billed from actual provider usage.
Checking current pricing…
Checking current pricing…
Quick take
- llama-4-maverick has a larger context window.
- claude-haiku-5-5 recorded higher recent LLM7 stability during this period.
- llama-4-maverick recorded a lower observed p95 API latency on LLM7 during this period.