Data points: 50
Model compare
The readout for Devstral 2 and GPT-5.2, before the detailed comparison sheet.
Weighted outcome: GPT-5.2. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
Decision read
GPT-5.2
GPT-5.2 has the higher weighted result; Model A / B score 10 to 90.
Evidence depth
50 data points
Includes 8 benchmark rows, 0 audit samples, and 5 provider examples.
Selection signal
Start with GPT-5.2
The charts below split 13 high-signal samples across speed, scores, and audit health.
Switch either side of this report to compare another model with the same LMSpeed data pipeline.
Select a different model to open a new comparison URL.
This report only uses LMSpeed data for Devstral 2 and GPT-5.2: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
| Model compare | Devstral 2 | GPT-5.2 |
|---|---|---|
| Overall leader | Contender | Leading |
| Weighted overall score | 10.0 pts | 90.0 pts |
| Benchmark category leads | 0 categories | 3 categories |
| Operational advantages | Average speed, First-token latency | Free providers, Provider coverage |
| Context window | No data | 400K tokens |
| Max output | No data | 128K tokens |
| Modalities | No data | Input FileImageText Output Text |
The overall result weights benchmark capability categories at 80% and price, API speed/latency, and availability at 20%. Recent test volume does not affect the winner, and missing benchmark categories are excluded.
| Model compare | Devstral 2 | GPT-5.2 |
|---|---|---|
| Developer | No data | OpenAI |
| Released | No data | Dec 2025 |
| Parameters | No data | No data |
| Tokenizer | No data | GPT |
| Knowledge cutoff | No data | No data |
| OpenRouter ID | No data | openai/gpt-5.2 |
| References | No data | No data |
This report only uses LMSpeed data for Devstral 2 and GPT-5.2: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
Devstral 2
Devstral 2 has these operational advantages: Average speed, First-token latency.
GPT-5.2
GPT-5.2 is stronger in benchmark categories (Coding, Reasoning, Math) and operational dimensions (Free providers, Provider coverage).
Third-party benchmark profile synced into LMSpeed; only metrics available for both models are shown.
Compare benchmark category scores on a 0-100 scale. Select a category to inspect the gap.
Avg. score
Devstral 2
45.2
Avg. score
GPT-5.2
54.3
GPT-5.2
GPT-5.2 leads by 10.4
GPT-5.2 leads by 9.4
GPT-5.2
GPT-5.2 leads by 12.6
GPT-5.2
GPT-5.2
GPT-5.2
Metric-level scores with benchmark source, rank depth, confidence, error, and evaluation date where available.
Devstral 2
0.71 s
Rank #25/139 · confidence 4
GPT-5.2
winner0.62 s
Rank #17/139 · confidence 4
Devstral 2
0.71 s
Rank #34/139 · confidence 4
GPT-5.2
winner0.62 s
Rank #25/139 · confidence 4
Devstral 2
60.4 tok/s
Rank #95/139 · confidence 4
GPT-5.2
winner62.2 tok/s
Rank #92/139 · confidence 4
Devstral 2
76.2%
Rank #80/125 · confidence 4
GPT-5.2
winner81.4%
Rank #54/125 · confidence 4
Devstral 2
3.6%
Rank #172/186 · confidence 4
GPT-5.2
winner7.3%
Rank #108/186 · confidence 4
Devstral 2
59.4%
Rank #141/187 · confidence 4
GPT-5.2
winner71.2%
Rank #110/187 · confidence 4
Devstral 2
44.8%
Rank #67/115 · confidence 4
GPT-5.2
winner66.9%
Rank #36/115 · confidence 4
Devstral 2
33.1%
Rank #120/184 · confidence 4
GPT-5.2
winner40.4%
Rank #63/184 · confidence 4
Latest completed audits from shared providers, with four safety and integrity score groups plus report links.
| Provider | Devstral 2 | GPT-5.2 |
|---|---|---|
| No completed audits are available from shared providers yet. | ||
Speed aggregates and input/output pricing share each provider row for real API selection and migration cost checks.
| Provider | Devstral 2 | GPT-5.2 |
|---|---|---|
0 tests | Devstral 2 speed / latency N/A / N/A input / output No data | GPT-5.2 speed / latency N/A / N/A input / output No data |
0 tests | Devstral 2 speed / latency N/A / N/A input / output No data | GPT-5.2 speed / latency N/A / N/A input / output No data |
0 tests | Devstral 2 speed / latency N/A / N/A input / output No data | GPT-5.2 speed / latency N/A / N/A input / output No data |
0 tests | Devstral 2 speed / latency N/A / N/A input / output No data | GPT-5.2 speed / latency N/A / N/A input / output No data |
0 tests | Devstral 2 speed / latency N/A / N/A input / output No data | GPT-5.2 speed / latency N/A / N/A input / output No data |
Weighted outcome: GPT-5.2. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
| Features | None listed | Text inputImage inputFile inputText outputTool callingStructured outputsJSON modeReasoning |
|---|
