← Niche Catalog

python_code_generation

Modality: llm_chat · full deep dive — every ranked model, test result, and artifact.

50
Models
342
Benchmark Results
0
Media Artifacts
0
Resolutions

Ranked Models

Ranked by confidence-adjusted score (single/zero-sample, non-curated scores floored; curated empirical scores trusted as-is).

#ModelProviderAdj. ScoreRawEvidence
1claude-sonnet-4-6claude_desktop0.7730.850n=50
2gpt-5.5::think=fastcodex0.5250.963n=6
3gpt-5.5::think=deepcodex0.5250.963n=6
4claude-opus-4-8::think=fastclaude_code0.4300.788n=6
5gpt-5.3-codex-spark::think=deepcodex0.3820.700n=6
6claude-opus-4-8::think=deepclaude_code0.3820.700n=6
7deepseek-reasonerdeepseek0.3560.800n=4
8grok-3-minixai0.3560.800n=4
9claude-opus-4-6anthropic0.3560.800n=4
10grok-4.20-multi-agent-0309xai0.3560.800n=4
11gemini-2.5-progoogle_gemini0.3460.778n=4
12gemini-2.5-flashgoogle_gemini0.3380.760n=4
13gpt-4oopenai0.3360.756n=4
14meta-llama/Llama-3.3-70B-Instruct-Turbotogether0.3360.756n=4
15deepseek-ai/DeepSeek-R1together0.3350.753n=4
16sonarperplexity0.3350.753n=4
17sonar-properplexity0.3350.753n=4
18grok-3xai0.3350.753n=4
19gpt-4.1-miniopenai0.3350.753n=4
20command-r-08-2024cohere0.3350.753n=4
21Qwen/Qwen2.5-7B-Instruct-Turbotogether0.3350.753n=4
22gpt-4o-miniopenai0.3350.753n=4
23deepseek-ai/DeepSeek-V3.1together0.3350.753n=4
24gpt-5.4::think=fastcodex0.3340.612n=6
25gpt-5.4::think=deepcodex0.3340.612n=6
26codex-auto-reviewcodex0.2860.525n=6
27gpt-5.3-codex-spark::think=fastcodex0.2860.525n=6
28magistral-small-latestmistral0.2590.583n=4
29mistral-large-latestmistral0.1850.417n=4
30claude-sonnet-4-6anthropic0.1200.803provisional (n≤1)
31claude-haiku-4-5-20251001anthropic0.1200.803provisional (n≤1)
32claude-sonnet-4-5-20250929claude_code0.1170.778provisional (n≤1)
33claude-opus-4-7anthropic0.1130.753provisional (n≤1)
34grok-4xai0.1130.753provisional (n≤1)
35gpt-4.1openai0.1130.753provisional (n≤1)
36gpt-5.1openai0.1130.753provisional (n≤1)
37o4-miniopenai0.1130.753provisional (n≤1)
38gpt-5-nanoopenai0.1130.753provisional (n≤1)
39claude-sonnet-4-20250514claude_code0.1070.714provisional (n≤1)
40claude-opus-4-1-20250805claude_code0.1030.690provisional (n≤1)
41claude-opus-4-20250514claude_code0.0880.586provisional (n≤1)
42claude-opus-4-5-20251101claude_code0.0860.574provisional (n≤1)
43claude-opus-4-8claude_code0.0630.422provisional (n≤1)
44deepseek-chatdeepseek0.0000.000n=4
45mistral-small-latestmistral0.0000.000n=4
46gpt-5openai0.0000.000provisional (n≤1)
47gpt-5-miniopenai0.0000.000provisional (n≤1)
48gpt-5.4codex0.0000.000n=50
49gpt-5.5codex0.0000.000provisional (n≤1)
50gpt-5.3-codex-sparkcodex0.0000.000n=50

Test Results

Showing top 25 of 342 benchmark outputs by weighted score.

claude-haiku-4-5-20251001 · anthropic · weighted 10.0 · syntactic_validity=10.0 · $0.000107 · 709ms

```python def add(a, b): return a + b ```

claude-haiku-4-5-20251001 · anthropic · weighted 10.0 · syntactic_validity=10.0, naming_conventions=10.0 · $0.000238 · 633ms

```python class UserProfile: def __init__(self): self.email = None def update_email(self, new_email): self.email = new_email ```

mistral-small-latest · mistral · weighted 10.0 · syntactic_validity=10.0 · $0.0 · 899ms

```python def add(a, b): return a + b ```

claude-opus-4-6 · anthropic · weighted 10.0 · syntactic_validity=10.0, naming_conventions=10.0 · $0.00327 · 1714ms

```python class UserProfile: def update_email(self, new_email): self.email = new_email ```

claude-haiku-4-5-20251001 · anthropic · weighted 10.0 · syntactic_validity=10.0 · $0.000107 · 881ms

```python def add(a, b): return a + b ```

gpt-4.1-mini · openai · weighted 10.0 · syntactic_validity=10.0, naming_conventions=10.0 · $0.0 · 1556ms

```python class UserProfile: def update_email(self, new_email): self.email = new_email ```

claude-sonnet-4-6 · anthropic · weighted 10.0 · syntactic_validity=10.0, naming_conventions=10.0 · $0.0 · 1420ms

```python class UserProfile: def update_email(self, new_email): self.email = new_email ```

gpt-4o-mini · openai · weighted 10.0 · syntactic_validity=10.0, naming_conventions=10.0 · $2.9e-05 · 939ms

```python class UserProfile: def __init__(self, email): self.email = email def update_email(self, new_email): self.email = new_email ```

deepseek-chat · deepseek · weighted 10.0 · syntactic_validity=10.0 · $8e-06 · 872ms

```python def add(a, b): return a + b ```

gemini-2.5-flash · google_gemini · weighted 10.0 · syntactic_validity=10.0 · $6.6e-05 · 863ms

```python def add(a, b): return a + b ```

sonar · perplexity · weighted 10.0 · syntactic_validity=10.0 · $4.5e-05 · 6096ms

```python def add(a, b): return a + b ```[1][3][5]

mistral-small-latest · mistral · weighted 10.0 · syntactic_validity=10.0 · $0.0 · 896ms

```python def add(a, b): return a + b ```

gpt-4o-mini · openai · weighted 10.0 · syntactic_validity=10.0 · $1.4e-05 · 894ms

```python def add(a, b): return a + b ```

deepseek-chat · deepseek · weighted 10.0 · syntactic_validity=10.0 · $8e-06 · 787ms

```python def add(a, b): return a + b ```

deepseek-chat · deepseek · weighted 10.0 · syntactic_validity=10.0, naming_conventions=10.0 · $1.2e-05 · 979ms

```python class UserProfile: def update_email(self, new_email): self.email = new_email ```

gpt-4o-mini · openai · weighted 10.0 · syntactic_validity=10.0 · $1.4e-05 · 745ms

```python def add(a, b): return a + b ```

gemini-2.5-flash · google_gemini · weighted 10.0 · syntactic_validity=10.0 · $6.6e-05 · 633ms

```python def add(a, b): return a + b ```

command-r-08-2024 · cohere · weighted 10.0 · syntactic_validity=10.0 · $0.0 · 769ms

```python def add(a, b): return a + b ```

mistral-large-latest · mistral · weighted 10.0 · syntactic_validity=10.0, naming_conventions=10.0 · $0.0 · 819ms

```python class UserProfile: def update_email(self, new_email): self.email = new_email ```

command-r-08-2024 · cohere · weighted 10.0 · syntactic_validity=10.0 · $0.0 · 963ms

```python def add(a, b): return a + b ```

grok-3 · xai · weighted 10.0 · syntactic_validity=10.0, naming_conventions=10.0 · $0.000396 · 1812ms

class UserProfile: def update_email(self, new_email): self.email = new_email

mistral-small-latest · mistral · weighted 10.0 · syntactic_validity=10.0, naming_conventions=10.0 · $0.0 · 1790ms

```python class UserProfile: def update_email(self, new_email): self.email = new_email ```

gpt-4o · openai · weighted 10.0 · syntactic_validity=10.0, naming_conventions=10.0 · $0.000485 · 744ms

```python class UserProfile: def __init__(self, email): self.email = email def update_email(self, new_email): self.email = new_email ```

sonar · perplexity · weighted 10.0 · syntactic_validity=10.0 · $4.3e-05 · 2045ms

```python def add(a, b): return a + b ```[3][5]

grok-3-mini · xai · weighted 10.0 · syntactic_validity=10.0 · $1.4e-05 · 2937ms

def add(a, b): return a + b