#90 Mistral Small 4
none- Cost
- $0.002
- Time
- 10.4s
- Tokens
- 2,370 tok
Mistral
Release: 2026-03-16
Tested on: 2026-04-11 01:44
mistralai/mistral-small-2603::none
(medium)
(none)
Summary
Mistral Small 4 scores 5.2 on AI BENCHY and ranks #90. It has N/A reliability, a 31.5% pass rate, $0.006 total cost, and 665ms average response time.
What makes Mistral Small 4 unique: It is notably fast compared with similar models.
5.2
Consistency
9.5
N/A
$0.006
Total Output Tokens
2,207
Total Input Tokens
0
Input Price
$0.150 / 1M
Output Price
$0.600 / 1M
Flaky tests
1
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 13:41 New test added | 4.9 | 10.0 | $0.007 | Compare | |
| 2026-05-22 00:14 Suite changed | 5.0 | 10.0 | $0.007 | Compare | |
| 2026-04-11 01:44 First recorded run | 5.2 | N/A | $0.006 | Current run |
Run comparison
| Run | Score | Consistency | Reliability | Tests Correct | Flaky tests | Total Output Tokens | Total Input Tokens | Total Cost | Response Time (avg) |
|---|---|---|---|---|---|---|---|---|---|
| 2026-04-11 01:44 · First recorded run | 5.2 | 9.5 | N/A | 5/18 | 1 | 2,207 | 0 | $0.006 | 665ms |
| 2026-06-04 13:41 · New test added | 4.9 | 9.5 | 10.0 | 5/21 | 1 | 2,201 | 37,309 | $0.007 | 630ms |
| Difference | +0.3 | 0.0 | 0 | 0 | +6 | -37309 | -$0.002 | +35ms |
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 4nonevsGLM 5V TurbononeMistral Small 4nonevsQwen3.5-27BnoneMistral Small 4nonevsQwen3.5-35B-A3BnoneMistral Small 4nonevsGemini 3.5 FlashhighMistral Small 4nonevsGemini 3 Flash PreviewmediumMistral Small 4nonevsNemotron 3 Ultra 550b A55bmediumFree AvailableMistral Small 4nonevsGPT-5.5low
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 3.4 | 7.9 | |
| Coding | 4.5 | 9.0 | |
| Combined | 3.0 | 10.0 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 5.3 | 10.0 | |
| General Intelligence | 4.0 | 10.0 | |
| Instructions following | 6.5 | 10.0 | |
| Puzzle Solving | 3.1 | 9.9 | |
| Tool Calling | 10.0 | 10.0 |