codestral-latest
Checking current pricing…
Chat comparison
codestral-latestvsgemini-3.6-flash-high
Compare the things that matter before you build: current price, capabilities, and latest aggregated LLM7 statistics.
Current pricing
See the cost difference clearly
gemini-3.6-flash-high
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.
Input formats
codestral-latest
text
gemini-3.6-flash-high
text, json
Reasoning
codestral-latest
Not supported
gemini-3.6-flash-highBetter fit
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%+
codestral-latest · leads in 1
28%
Weak
gemini-3.6-flash-high · leads in 28
71%
Moderate
Knowledge & reasoning
General knowledge
codestral-latest9%gemini-3.6-flash-highLeads73%Logical reasoning
codestral-latest10%gemini-3.6-flash-highLeads70%Mathematics
codestral-latest25%gemini-3.6-flash-highLeads73%Scientific and technical depth
codestral-latest15%gemini-3.6-flash-highLeads68%Planning and task decomposition
codestral-latest11%gemini-3.6-flash-highLeads67%
Coding & tools
Code generation
codestral-latestLeads85%gemini-3.6-flash-high65%Debugging and code review
codestral-latest60%gemini-3.6-flash-highLeads69%Agentic coding
codestral-latest44%gemini-3.6-flash-highLeads69%Tool and function calling
codestral-latest33%gemini-3.6-flash-highLeads76%SQL and query writing
codestral-latest60%gemini-3.6-flash-highLeads73%
Writing & language
Creative writing
codestral-latest7%gemini-3.6-flash-highLeads56%Professional writing
codestral-latest8%gemini-3.6-flash-highLeads64%Conversational quality
codestral-latest7%gemini-3.6-flash-highLeads65%Multilingual ability
codestral-latest32%gemini-3.6-flash-highLeads99%Translation
codestral-latest11%gemini-3.6-flash-highLeads77%Summarization
codestral-latest7%gemini-3.6-flash-highLeads53%
Data & professional work
Data analysis
codestral-latest13%gemini-3.6-flash-highLeads77%Professional domains
codestral-latest5%gemini-3.6-flash-highLeads65%Information extraction
codestral-latest16%gemini-3.6-flash-highLeads78%Classification and labeling
codestral-latest15%gemini-3.6-flash-highLeads85%Long-context handling
codestral-latest15%gemini-3.6-flash-highLeads37%
Reliability & control
Instruction following
codestral-latest21%gemini-3.6-flash-highLeads70%Structured output
codestral-latest44%gemini-3.6-flash-highLeads87%Factual accuracy
codestral-latest17%gemini-3.6-flash-highLeads73%Safety and alignment
codestral-latest14%gemini-3.6-flash-highLeads69%Steerability
codestral-latest14%gemini-3.6-flash-highLeads62%Output consistency
codestral-latest52%gemini-3.6-flash-highLeads77%
Speed, cost & vision
Response speed
codestral-latest85%gemini-3.6-flash-highLeads91%Cost efficiency
codestral-latest82%gemini-3.6-flash-highLeads84%Image understanding
codestral-latestNo image inputgemini-3.6-flash-highNo image input
Latest LLM7 statistics
Recent aggregated percentages and response-time metrics from LLM7, not a global model benchmark or traffic disclosure.
Recent stability
codestral-latest
98.36%
gemini-3.6-flash-high
99.2%
Average response time
codestral-latest
3,439.06 ms
gemini-3.6-flash-high
9,446.51 ms
P95 API latency
codestral-latest
10,000 ms
gemini-3.6-flash-high
30,000 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
codestral-latest: 99.3%gemini-3.6-flash-high: 85.7%
Average API latency
Both models on the same scale
codestral-latest: 4,108 msgemini-3.6-flash-high: 24,682 ms
P95 API latency
Both models on the same scale
codestral-latest: 10,000 msgemini-3.6-flash-high: 60,000 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
- The recent stability rates are too close to distinguish meaningfully.
- codestral-latest recorded a lower observed p95 API latency on LLM7 during this period.