#121 Mistral Small 4
medium- Cost
- $0.006
- Time
- 47.9s
- Tokens
- 9,857 tok
Mistral
Release: 2026-03-16
Tested on: 2026-05-22 00:16
mistralai/mistral-small-2603::medium
(medium)
(none)
Summary
Mistral Small 4 scores 5.4 on AI BENCHY and ranks #121. It has 10.0 reliability, a 45.0% pass rate, $0.056 total cost, and 8.33s average response time.
What makes Mistral Small 4 unique: It stands out most in Anti-AI Tricks, where it ranks #2, while Data parsing and extraction is its weakest area at #9. It uses unusually many reasoning tokens, which can help explain its slower or more expensive runs.
5.4
Consistency
7.1
10.0
$0.056
Total Output Tokens
89,683
Total Input Tokens
0
Input Price
$0.150 / 1M
Output Price
$0.600 / 1M
Flaky tests
7
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
Run history
| Tested on | Score | Reliability | Tests Correct | Total Cost | Compare |
|---|---|---|---|---|---|
| 2026-06-04 13:43 New test added | 5.3 | 10.0 | $0.068 | Compare | |
| 2026-05-22 00:16 Suite changed | 5.4 | 10.0 | $0.056 | Current run | |
| 2026-04-11 01:44 First recorded run | 5.7 | N/A | $0.034 | Compare |
This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.
Run comparison
| Run | Score | Consistency | Reliability | Tests Correct | Flaky tests | Total Output Tokens | Total Input Tokens | Total Cost | Response Time (avg) |
|---|---|---|---|---|---|---|---|---|---|
| 2026-05-22 00:16 · Suite changed | 5.4 | 7.1 | 10.0 | 5/20 | 7 | 89,683 | 0 | $0.056 | 8.33s |
| 2026-06-04 13:43 · New test added | 5.3 | 6.9 | 10.0 | 5/21 | 8 | 108,862 | 42,576 | $0.068 | 9.40s |
| Difference | +0.1 | +0.2 | 0.0 | 0 | -1 | -19179 | -42576 | -$0.012 | -1070ms |
These two runs used different benchmark suites, so the deltas reflect both model changes and suite changes.
Charts
Choose the first model, then click a second model to open a side-by-side page.
Top Models by Score
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Quick Compare
Mistral Small 4mediumvsQwen3.5 Plus 2026-02-15noneMistral Small 4mediumvsKimi K2.6noneFree AvailableMistral Small 4mediumvsGLM 5V TurbononeMistral Small 4mediumvsGPT-5.4noneMistral Small 4mediumvsGemini 3.5 FlashhighMistral Small 4mediumvsGemini 3 Flash PreviewmediumMistral Small 4mediumvsNemotron 3 Ultra 550b A55bmediumFree AvailableMistral Small 4mediumvsGPT-5.5low
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 5.6 | 3.8 | |
| Coding | 5.1 | 6.8 | |
| Combined | 3.0 | 10.0 | |
| Data parsing and extraction | 7.3 | 5.9 | |
| Domain specific | 5.3 | 7.2 | |
| General Intelligence | 4.8 | 10.0 | |
| Instructions following | 7.3 | 5.8 | |
| Puzzle Solving | 3.4 | 9.7 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |