codestral-latest
Checking current pricing…
Chat comparison
codestral-latestvsmistral-large-3:675b
Compare the things that matter before you build: current price, capabilities, and latest aggregated LLM7 statistics.
Current pricing
See the cost difference clearly
mistral-large-3:675b
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
codestral-latest
32,000 tokens
mistral-large-3:675bBetter fit
256,000 tokens
Input formats
codestral-latest
text
mistral-large-3:675b
text, image
Vision
codestral-latest
Not supported
mistral-large-3:675bBetter fit
Supported
JSON mode
codestral-latestBetter fit
Supported
mistral-large-3:675b
Not supported
Reasoning
codestral-latest
Not supported
mistral-large-3:675bBetter 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 6
28%
Weak
mistral-large-3:675b · leads in 23
49%
Weak
Knowledge & reasoning
General knowledge
codestral-latest9%mistral-large-3:675bLeads52%Logical reasoning
codestral-latest10%mistral-large-3:675bLeads57%Mathematics
codestral-latest25%mistral-large-3:675bLeads62%Scientific and technical depth
codestral-latest15%mistral-large-3:675bLeads62%Planning and task decomposition
codestral-latest11%mistral-large-3:675bLeads55%
Coding & tools
Code generation
codestral-latestLeads85%mistral-large-3:675b49%Debugging and code review
codestral-latestLeads60%mistral-large-3:675b56%Agentic coding
codestral-latest44%mistral-large-3:675bLeads54%Tool and function calling
codestral-latest33%mistral-large-3:675bLeads54%SQL and query writing
codestral-latestLeads60%mistral-large-3:675b55%
Writing & language
Creative writing
codestral-latest7%mistral-large-3:675bLeads50%Professional writing
codestral-latest8%mistral-large-3:675bLeads49%Conversational quality
codestral-latest7%mistral-large-3:675bLeads50%Multilingual ability
codestral-latest32%mistral-large-3:675bLeads86%Translation
codestral-latest11%mistral-large-3:675bLeads59%Summarization
codestral-latest7%mistral-large-3:675bLeads45%
Data & professional work
Data analysis
codestral-latest13%mistral-large-3:675bLeads54%Professional domains
codestral-latest5%mistral-large-3:675bLeads56%Information extraction
codestral-latest16%mistral-large-3:675bLeads33%Classification and labeling
codestral-latest15%mistral-large-3:675bLeads54%Long-context handling
codestral-latest15%mistral-large-3:675bLeads44%
Reliability & control
Instruction following
codestral-latest21%mistral-large-3:675bLeads36%Structured output
codestral-latestLeads44%mistral-large-3:675b9%Factual accuracy
codestral-latest17%mistral-large-3:675bLeads52%Safety and alignment
codestral-latest14%mistral-large-3:675bLeads45%Steerability
codestral-latest14%mistral-large-3:675bLeads46%Output consistency
codestral-latest52%mistral-large-3:675bLeads54%
Speed, cost & vision
Response speed
codestral-latestLeads85%mistral-large-3:675b34%Cost efficiency
codestral-latestLeads82%mistral-large-3:675b48%Image understanding
codestral-latestNo image inputmistral-large-3:675b17%
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%
mistral-large-3:675b
100%
Average response time
codestral-latest
3,439.06 ms
mistral-large-3:675b
17,950.15 ms
P95 API latency
codestral-latest
10,000 ms
mistral-large-3:675b
60,000 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%mistral-large-3:675b: 100%
Average API latency
Both models on the same scale
codestral-latest: 4,108 msmistral-large-3:675b: 15,337 ms
P95 API latency
Both models on the same scale
codestral-latest: 10,000 msmistral-large-3:675b: 30,000 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
- mistral-large-3:675b has a larger context window.
- mistral-large-3:675b supports image input while the other model does not.
- mistral-large-3:675b recorded higher recent LLM7 stability during this period.
- codestral-latest recorded a lower observed p95 API latency on LLM7 during this period.