Intent2Tx - 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, without 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, direct inference without demonstrations; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 15 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Flash | 61.6 | #463 |
| 2 | Gemini 2.5 Pro | 60.5 | #276 |
| 3 | GLM-4.6 | 59.2 | #498 |
| 4 | Kimi K2 0905 | 56 | #570 |
| 5 | GPT-5.2 | 54.1 | #185 |
| 6 | Qwen3 Coder Next | 52 | #725 |
| 7 | Claude Haiku 4.5 | 51.3 | #583 |
| 8 | codestral-2508 | 48.1 | #1511 |
| 9 | DeepSeek V3.2 | 48 | #419 |
| 10 | Claude Opus 4.5 | 47.2 | #160 |
| 11 | Qwen 3 235B A22B 2507 Instruct | 40.9 | #616 |
| 12 | GPT-5.2 Codex | 39.4 | #182 |
| 13 | GLM-4 32B (0414) | 37.7 | #1505 |
| 14 | Llama 3.3 70B Instruct | 31 | #1385 |
| 15 | Llama 3.1 8B Instruct | 20.8 | #4600 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=intent2tx-state-equivalence · How It Works · Data refreshed daily, snapshot 2026-11-21.