claude-haiku-4-5
Checking current pricing…
Chat comparison
claude-haiku-4-5vscodestral-latest
Compare the things that matter before you build: current price, capabilities, and latest aggregated LLM7 statistics.
Current pricing
See the cost difference clearly
codestral-latest
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-4-5Better fit
200,000 tokens
codestral-latest
32,000 tokens
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-4-5 · leads in 23
48%
Weak
codestral-latest · leads in 6
28%
Weak
Knowledge & reasoning
General knowledge
claude-haiku-4-5Leads44%codestral-latest9%Logical reasoning
claude-haiku-4-5Leads23%codestral-latest10%Mathematics
claude-haiku-4-5Leads29%codestral-latest25%Scientific and technical depth
claude-haiku-4-5Leads26%codestral-latest15%Planning and task decomposition
claude-haiku-4-5Leads25%codestral-latest11%
Coding & tools
Code generation
claude-haiku-4-537%codestral-latestLeads85%Debugging and code review
claude-haiku-4-531%codestral-latestLeads60%Agentic coding
claude-haiku-4-532%codestral-latestLeads44%Tool and function calling
claude-haiku-4-5Leads49%codestral-latest33%SQL and query writing
claude-haiku-4-536%codestral-latestLeads60%
Writing & language
Creative writing
claude-haiku-4-5Leads45%codestral-latest7%Professional writing
claude-haiku-4-5Leads56%codestral-latest8%Conversational quality
claude-haiku-4-5Leads53%codestral-latest7%Multilingual ability
claude-haiku-4-5Leads44%codestral-latest32%Translation
claude-haiku-4-5Leads45%codestral-latest11%Summarization
claude-haiku-4-5Leads43%codestral-latest7%
Data & professional work
Data analysis
claude-haiku-4-5Leads33%codestral-latest13%Professional domains
claude-haiku-4-5Leads39%codestral-latest5%Information extraction
claude-haiku-4-5Leads50%codestral-latest16%Classification and labeling
claude-haiku-4-5Leads50%codestral-latest15%Long-context handling
claude-haiku-4-5Leads41%codestral-latest15%
Reliability & control
Instruction following
claude-haiku-4-5Leads55%codestral-latest21%Structured output
claude-haiku-4-5Leads70%codestral-latest44%Factual accuracy
claude-haiku-4-5Leads63%codestral-latest17%Safety and alignment
claude-haiku-4-5Leads68%codestral-latest14%Steerability
claude-haiku-4-5Leads59%codestral-latest14%Output consistency
claude-haiku-4-5Leads86%codestral-latest52%
Speed, cost & vision
Response speed
claude-haiku-4-584%codestral-latestLeads85%Cost efficiency
claude-haiku-4-568%codestral-latestLeads82%Image understanding
claude-haiku-4-5No image inputcodestral-latestNo image input
Latest LLM7 statistics
Recent aggregated percentages and response-time metrics from LLM7, not a global model benchmark or traffic disclosure.
Recent stability
claude-haiku-4-5
96.36%
codestral-latest
98.36%
Average response time
claude-haiku-4-5
5,956.97 ms
codestral-latest
3,439.06 ms
P95 API latency
claude-haiku-4-5
30,000 ms
codestral-latest
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-4-5: 100%codestral-latest: 99.3%
Average API latency
Both models on the same scale
claude-haiku-4-5: 3,702 mscodestral-latest: 4,108 ms
P95 API latency
Both models on the same scale
claude-haiku-4-5: 30,000 mscodestral-latest: 10,000 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
- claude-haiku-4-5 has a larger context window.
- codestral-latest recorded higher recent LLM7 stability during this period.
- codestral-latest recorded a lower observed p95 API latency on LLM7 during this period.