Intent2Tx (Retrieval) - State Equivalence: leaderboard
Intent2Tx (2026) evaluates LLMs on translating natural-language Web3 intents into executable Ethereum transactions, with instances derived from real mainnet traces across eleven protocol categories. This board is the percentage of single-step transactions whose execution on a forked mainnet changes account state like the reference, with three retrieved demonstrations; higher is better.
Metric: State equivalence (from 0-1, times 100): share of generated single-step transactions whose execution on a forked Ethereum mainnet (fork one block before the original transaction) changes account-level state like the reference transaction (within 1%), over instances whose reference executes, with the three most similar instances retrieved as demonstrations; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 16 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.5 | 70.6 | #165 |
| 2 | Gemini 2.5 Pro | 70.2 | #280 |
| 3 | GPT-5.2 | 69.7 | #190 |
| 4 | Qwen3 Coder Next | 69.7 | #741 |
| 5 | GPT-5.2 Codex | 69.7 | #186 |
| 6 | Gemini 2.5 Flash | 69.2 | #466 |
| 7 | GLM-4.6 | 67.2 | #496 |
| 8 | Kimi K2 0905 | 65.5 | #578 |
| 9 | Qwen 3 235B A22B 2507 Instruct | 65.3 | #625 |
| 10 | Claude Haiku 4.5 | 64.7 | #587 |
| 11 | GLM-4 32B (0414) | 64.3 | #1525 |
| 12 | DeepSeek V3.2 | 63.5 | #425 |
| 13 | codestral-2508 | 62.6 | #1522 |
| 14 | Llama 3.3 70B Instruct | 57.3 | #1394 |
| 15 | Ministral 3 14B | 52.3 | #1885 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=intent2tx-retrieval-state-equivalence · How It Works · Data refreshed daily, snapshot 2026-11-22.