The Inference Report
March 23, 2026
The Value FrontierDaily rankings from SWE-rebench, a benchmark designed to fairly compare LLM capabilities on real-world software engineering tasks. Unlike other evaluations, it uses a standardized scaffolding for all models, continuously updates its dataset to prevent contamination, and runs each model five times to account for stochastic variance.
| # | Model | Score |
|---|---|---|
| 1 | Claude Code | 52.9% |
| 2 | Junie | 52.1% |
| 3 | Claude Opus 4.6 | 51.7% |
| 4 | gpt-5.2-2025-12-11-xhigh | 51.7% |
| 5 | gpt-5.2-2025-12-11-medium | 51.0% |
| 6 | gpt-5.1-codex-max | 48.5% |
| 7 | Claude Sonnet 4.5 | 47.1% |
| 8 | Gemini 3 Pro Preview | 46.7% |
| 9 | Gemini 3 Flash Preview | 46.7% |
| 10 | gpt-5.2-codex | 45.0% |
Artificial Analysis composite index across coding, math, and reasoning benchmarks.
| # | Model | Score | tok/s | $/1M |
|---|---|---|---|---|
| 1 | GPT-5.4 | 57.2 | 84 | $5.63 |
| 2 | Gemini 3.1 Pro Preview | 57.2 | 123 | $4.50 |
| 3 | GPT-5.3 Codex | 54 | 68 | $4.81 |
| 4 | Claude Opus 4.6 | 53 | 50 | $10.00 |
| 5 | Claude Sonnet 4.6 | 51.7 | 65 | $6.00 |
| 6 | GPT-5.2 | 51.3 | 75 | $4.81 |
| 7 | GLM-5 | 49.8 | 89 | $1.55 |
| 8 | Claude Opus 4.5 | 49.7 | 58 | $10.00 |
| 9 | MiniMax-M2.7 | 49.6 | 44 | $0.525 |
| 10 | MiMo-V2-Pro | 49.2 | 0 | $0.00 |
Output tokens per second — higher is faster. Minimum intelligence score of 40.
| # | Model | tok/s |
|---|---|---|
| 1 | GPT-5.4 mini | 233 |
| 2 | GPT-5.4 nano | 216 |
| 3 | Gemini 3 Flash Preview | 186 |
| 4 | GPT-5 Codex | 172 |
| 5 | Qwen3.5 122B A10B | 158 |
| 6 | MiMo-V2-Flash | 142 |
| 7 | GPT-5.1 Codex | 130 |
| 8 | GPT-5.1 | 126 |
| 9 | Gemini 3.1 Pro Preview | 123 |
| 10 | Gemini 3 Pro Preview | 120 |
Blended cost per 1M tokens (3:1 input/output) — lower is cheaper. Minimum intelligence score of 40.
| # | Model | $/1M |
|---|---|---|
| 1 | MiMo-V2-Flash | $0.15 |
| 2 | DeepSeek V3.2 | $0.315 |
| 3 | GPT-5.4 nano | $0.463 |
| 4 | MiniMax-M2.7 | $0.525 |
| 5 | MiniMax-M2.5 | $0.525 |
| 6 | GPT-5 mini | $0.688 |
| 7 | Qwen3.5 27B | $0.825 |
| 8 | GLM-4.7 | $1.00 |
| 9 | Kimi K2 Thinking | $1.07 |
| 10 | Qwen3.5 122B A10B | $1.10 |