Code generation and understanding
10
Models
9
Benchmarks
5
Providers
7
Open Weight
9
Deployable Now
7 self-host
10
Structured benchmark-backed rows
0
Signal-backed rows without full normalized tables
0
Benchmark-expected rows still catching up
| # | Model | Capability | Quality | Params | TerminalBench 2.0 | SWE-Bench | MMLU | GPQA | $/M In | Speed | Open |
|---|---|---|---|---|---|---|---|---|---|---|---|
1 | GPT-5.1 Codex OpenAI Subscription |
| 63.1 |
| 41.8 |
| Undisclosed |
| 57.8 |
| 66.0 |
| — |
| — |
$1.25/M Cheapest verified |
| — |
11 | Grok Code Fast 1 xAI SubscriptionStructured | 60.3 | 23.0 | Undisclosed | 25.8 | — | 79.3 | 72.7 | $0.2000/M Cheapest verified | — |
5 | CodeLlama 70B Meta Open WeightsStructured | 52.0 | 59.9 | 70B | — | 42.4 | — | — | Free Free | — |
4 | Qwen3 Next 80B A3B Instruct Qwen Open WeightsStructured | 47.3 | 24.8 | 80B | — | 42.4 | 81.9 | 73.8 | $0.0900/M Cheapest verified | — |
6 | Qwen3 Coder 30B A3B Instruct Qwen Open WeightsStructured | 40.5 | 23.3 | 30B | — | 51.6 | 70.6 | 51.6 | $0.0700/M Cheapest verified | — |
7 | Devstral Medium Mistral AI Open WeightsStructured | 39.5 | 23.5 | Unknown | — | — | 70.8 | 49.2 | $0.4000/M Cheapest verified | — |
9 | Qwen3 Coder Flash Qwen Open WeightsStructured | 37.2 | 21.9 | Unknown | — | 69.6 | — | — | $0.1950/M Cheapest verified | — |
8 | Qwen3 Coder Plus Qwen Open WeightsStructured | 35.0 | 21.4 | Unknown | — | — | — | — | $0.6500/M Cheapest verified | — |
12 | qwen-2.5-coder-32b-instruct Qwen Open WeightsStructured | 19.9 | 15.2 | 32B | — | 40.2 | — | — | $0.6600/M Cheapest verified | — |
13 | Codex Mini OpenAI Structured | — | — | Undisclosed | 43.1 | — | — | — | $1.50/M Cheapest verified | — |