Retrospective LLM-Based Complexity Evaluations

Prospective · frozen 2026-08-26 snapshot

Hegotá candidate complexity assessment

Original PFI result: 776 across 37 scored EIPs. The SFI/CFI extension adds 80 across 2 scored EIPs, producing a combined visibility view of 856 across 39 scored Execution Layer surfaces. 7 PFI entries remain not applicable or explicitly excluded.

Independent LLM Evaluation. These scores were produced with an LLM using the same Execution Layer complexity-assignment rubric, independently of the STEEL team’s ongoing manual assessment work. The Human column below records where that manual work stands for each candidate.
Common information cutoff: 2026-08-25T11:56:58Z. The assessment covers Execution Layer and execution-client networking surfaces only. It does not predict final fork scope or include observed outcomes.
Scored EL surfaces
39
7 not applicable
Low / Medium / High
4 / 21 / 14
Under-specified at snapshot
36 / 39
Human checklists
25 of 46
  • Complete 2
  • Available in open PR 15
  • Draft PR 8
  • Pending 21
22 same-rubric Human/LLM comparisons
Human checklist sources: ethspecs/pm at 2026-08-14 plus 24 open pull requests (captured 2026-09-13)

Statuses follow the real source state. Complete is merged on main; Available in open PR exists only in an open pull request; Draft PR is in a draft pull request; Incomplete has unresolved cells or inconsistent totals and carries no score; Pending has no checklist anywhere. A missing checklist is never a zero.

Where the Complexity Comes From

Each segment sums one criterion across the fork's scored LLM assessments. Hover or focus a segment for its points, share, and the number of contributing EIPs.

View
Hegotá856 points · 39 EIPs
Composition table: points per criterion and fork
Hegotá: criterion points across 39 scored candidates
CriterionHegotá
Added opcodes18 · 2% · 8 EIPs
Modified opcodes36 · 4% · 12 EIPs
Modified precompiles7 · 1% · 3 EIPs
Added system contracts16 · 2% · 9 EIPs
Modified system contracts4 · 0% · 4 EIPs
EVM Gas rule changes39 · 5% · 23 EIPs
State-access ordering within opcode execution19 · 2% · 10 EIPs
Blob gas accounting changes2 · 0% · 1 EIP
State gas accounting changes7 · 1% · 4 EIPs
New EVM gas refund4 · 0% · 2 EIPs
New transaction types3 · 0% · 1 EIP
New or modified transaction validity mechanisms21 · 2% · 9 EIPs
New block / header fields6 · 1% · 2 EIPs
Encoding changes (RLP/SSZ)33 · 4% · 11 EIPs
Block syncing changes12 · 1% · 6 EIPs
New fork activation mechanism30 · 4% · 10 EIPs
Engine API changes9 · 1% · 4 EIPs
Transition-tool interface changes15 · 2% · 7 EIPs
Patterns affecting pre-existing tests69 · 8% · 37 EIPs
New invariant on pre-existing tests22 · 3% · 14 EIPs
New test-framework primitives16 · 2% · 11 EIPs
Security risks93 · 11% · 38 EIPs
Performance risks75 · 9% · 34 EIPs
Edge/boundary conditions106 · 12% · 39 EIPs
Cryptography13 · 2% · 8 EIPs
Cross-EIP interactions105 · 12% · 36 EIPs
Unspecified behavior requiring cross-client consensus76 · 9% · 34 EIPs
Total856

Complexity Assessments

LLM rows were automated using the GPT-5.6 Sol LLM at xhigh reasoning effort, evaluating the EIP revision linked in the Assessment Input column against version 2 of STEEL’s complexity-assignment template. Human rows are STEEL reviewers’ published checklists; their status badge links to the pull request or merged report. Select rows from either evaluator to compare them, or open an EIP for its full assessment.

Totals and charts use the original 2026-08-26 candidate snapshot. The table retains every published evaluation, grouped by EIP with newer evaluations first. Evaluation dates link to the assessed spec revision; human checklist evaluation dates are not recorded.

Evaluator
65 assessments: 40 LLM, 25 Human· 21 Hegotá candidates have a pending human checklist
Hegotá 2026-08-26 candidate snapshot: all published evaluations, with not-applicable entries and pending human checklists counted above
Select for comparisonComplexity profile
EIP-2488 Deprecate the CALLCODE opcodePFILLMChecklist v2Complete10LowYes
EIP-2488 Deprecate the CALLCODE opcodePFINot recordedHumanChecklist v2Open PR13Medium
EIP-3298 Remove storage-clear refund and refund capPFILLMChecklist v2Complete12MediumNo
EIP-3298 Remove storage-clear refund and refund capPFINot recordedHumanChecklist v2Open PR6Low
EIP-4758 Deactivate SELFDESTRUCTPFILLMChecklist v2Complete14MediumYes
EIP-4758 Deactivate SELFDESTRUCTPFINot recordedHumanChecklist v2Open PR8Low
EIP-5920 PAY opcodePFILLMChecklist v2Complete16MediumYes
EIP-5920 PAY opcodePFINot recordedHumanChecklist v2Open PR14Medium
EIP-7645 Alias ORIGIN to SENDERPFILLMChecklist v2Complete11LowYes
EIP-7645 Alias ORIGIN to SENDERPFINot recordedHumanChecklist v2Open PR8Low
EIP-7666 EVM-ify the identity precompilePFILLMChecklist v2Complete15MediumNo
EIP-7666 EVM-ify the identity precompilePFINot recordedHumanChecklist v2Draft PR12Medium
EIP-7668 Remove bloom filtersPFILLMChecklist v2Complete10LowYes
EIP-7668 Remove bloom filtersPFINot recordedHumanChecklist v2Open PR7Low
EIP-7709 Read BLOCKHASH from Storage and Update CostPFILLMChecklist v2Complete20MediumYes
EIP-7709 Read BLOCKHASH from Storage and Update CostPFINot recordedHumanChecklist v2Open PR17Medium
EIP-7805 Fork-choice enforced Inclusion Lists (FOCIL)SFILLMChecklist v2Complete20MediumYes
EIP-7805 Fork-choice enforced Inclusion Lists (FOCIL)SFINot recordedHumanChecklist v1Complete15Medium
EIP-7807 SSZ execution blocksPFILLMChecklist v2Complete34HighYes
EIP-7819 SETDELEGATE instructionPFILLMChecklist v2Complete21MediumYes
EIP-7819 SETDELEGATE instructionPFINot recordedHumanChecklist v2Draft PR22Medium
EIP-7851 Code-Controlled EOA DelegationPFILLMChecklist v2Complete23HighYes
EIP-7862 Delayed State RootPFILLMChecklist v2Complete14MediumNo
EIP-7862 Delayed State RootPFINot recordedHumanChecklist v2Open PR19
published 26
Medium
EIP-7906 Transaction Assertions via State Diff OpcodePFILLMChecklist v2Complete28HighYes
EIP-7906 Transaction Assertions via State Diff OpcodePFINot recordedHumanChecklist v2Open PR23High
EIP-7923 Linear, Page-Based Memory CostingPFILLMChecklist v2Complete23HighYes
EIP-7923 Linear, Page-Based Memory CostingPFINot recordedHumanChecklist v2Open PR15Medium
EIP-7979 Call and Return Opcodes for the EVMPFILLMChecklist v2Complete16MediumYes
EIP-8025 Optional Execution ProofsPFILLMChecklist v2Complete21MediumYes
EIP-8077 eth/XX - announce transactions with noncePFILLMChecklist v2Complete15MediumYes
EIP-8094 eth/vhash - Blob-Aware MempoolPFILLMChecklist v2Complete20MediumYes
EIP-8115 Batch priority fees at end of blockPFILLMChecklist v2Complete16MediumYes
EIP-8115 Batch priority fees at end of blockPFINot recordedHumanChecklist v2Draft PR10Low
EIP-8116 Replace cumulative receipt fieldsPFILLMChecklist v2Complete10LowYes
EIP-8131 Unified Transaction Content FloorPFILLMChecklist v2Complete18MediumYes
EIP-8141 Frame TransactionCFILLMChecklist v2Complete60HighYes
EIP-8141 Frame TransactionCFINot recordedHumanChecklist v1Complete38High
EIP-8146 Block Access List SidecarsPFILLMChecklist v2Complete20MediumYes
EIP-8146 Block Access List SidecarsPFINot recordedHumanChecklist v2Open PR19Medium
EIP-8148 Custom sweep threshold for validatorsPFILLMChecklist v2Complete27HighYes
EIP-8151 Account Code Restricted ecRecoverPFILLMChecklist v2Complete22MediumYes
EIP-8182 Private ETH and ERC-20 TransfersPFILLMChecklist v2Complete20MediumYes
EIP-8188 Last-Written Block for Accounts and SlotsPFILLMChecklist v2Complete26HighYes
EIP-8188 Last-Written Block for Accounts and SlotsPFINot recordedHumanChecklist v2Open PR18Medium
EIP-8200 EVMificationPFILLMChecklist v2Complete28HighYes
EIP-8200 EVMificationPFINot recordedHumanChecklist v2Draft PR22Medium
EIP-8205 Withdrawal credentials preregistrationPFILLMChecklist v2Complete24HighYes
EIP-8205 Withdrawal credentials preregistrationPFINot recordedHumanChecklist v1Open PR5Low
EIP-8237 Independent CL/EL SyncPFILLMChecklist v2Complete29HighYes
EIP-8250 Keyed Nonces for Frame TransactionsPFILLMChecklist v2Complete42HighYes
EIP-8250 Keyed Nonces for Frame TransactionsPFINot recordedHumanChecklist v2Draft PR22
published 20
Medium
EIP-8253 Bump nonce of zero-nonce storage accountsPFILLMChecklist v2Complete20MediumYes
EIP-8272 Recent Roots for Frame TransactionsPFI
Re-evaluation
LLMChecklist v2Complete24HighYes
EIP-8272 Recent Roots for Frame TransactionsPFILLMChecklist v2Complete39HighYes
EIP-8272 Recent Roots for Frame TransactionsPFINot recordedHumanChecklist v2Open PR14Medium
EIP-8279 Block Access List Byte FloorPFILLMChecklist v2Complete29HighYes
EIP-8279 Block Access List Byte FloorPFINot recordedHumanChecklist v2Draft PR22Medium
EIP-8298 SETCODEFROM Code Reuse InstructionPFILLMChecklist v2Complete22MediumYes
EIP-8304 Trustless log and transaction indexPFILLMChecklist v2Complete30HighYes
EIP-8304 Trustless log and transaction indexPFINot recordedHumanChecklist v2Open PR26High
EIP-8368 CPSB Recalibration for New Gas LimitPFILLMChecklist v2Complete12MediumYes
EIP-8368 CPSB Recalibration for New Gas LimitPFINot recordedHumanChecklist v2Draft PR16Medium
EIP-8372 Normalized state gas limitPFILLMChecklist v2Complete19MediumYes
EIP-8372 Normalized state gas limitPFINot recordedHumanChecklist v2Draft PR20Medium

Scored proposals

Every scored assessment as a stacked complexity bar, ranked by total on one shared scale. Switch evaluator to rank the human checklists, or show both per EIP. The seven not-applicable entries remain in the table above.

Evaluator
  1. EIP-8141 Frame TransactionCFIChecklist revision 2
  2. EIP-7807 SSZ execution blocksPFIChecklist revision 2
  3. EIP-8237 Independent CL/EL SyncPFIChecklist revision 2
  4. EIP-8200 EVMificationPFIChecklist revision 2
  5. EIP-7819 SETDELEGATE instructionPFIChecklist revision 2
  6. EIP-8025 Optional Execution ProofsPFIChecklist revision 2
  7. EIP-5920 PAY opcodePFIChecklist revision 2
  8. EIP-4758 Deactivate SELFDESTRUCTPFIChecklist revision 2
  9. EIP-7862 Delayed State RootPFIChecklist revision 2
  10. EIP-7645 Alias ORIGIN to SENDERPFIChecklist revision 2
  11. EIP-7668 Remove bloom filtersPFIChecklist revision 2

Caveats

Download all assessmentsPublication JSON
Criterion legend and glossary

Every stacked bar, comparison matrix, and criterion table on this site uses the same criterion colours, abbreviations, and order. Colour marks the criterion group; the abbreviation and name identify the criterion. Scores are 0–3 per criterion (4 is exceptional; cross-EIP interactions is uncapped).

EVM surface

Opcodes, precompiles, and system contracts that are added or modified.

  • Added opcodes
    Introduces new opcodes
  • Modified opcodes
    Modifies pre-existing opcodes
  • Added precompiles
    Introduces new precompiles
  • Modified precompiles
    Modifies pre-existing precompiles logic or gas-accounting
  • Added system contracts
    Introduces new system contract, stateful or not
  • Modified system contracts
    Modifies pre-existing system contracts

Gas and accounting

Execution, blob, and state gas rules, refunds, and where charges happen inside opcodes.

  • EVM Gas rule changes
    New EVM gas accounting rules
  • State-access ordering within opcode execution · Checklist revision 2 only
    Changes *where inside an opcode's execution* state is accessed, or where gas is charged relative to that access. Because a state access is recorded in the block-level access list only if execution had enough gas to reach it, this ordering is consensus-critical: moving it changes the BAL at every gas boundary of every affected opcode.
  • Blob gas accounting changes
    New Blob gas accounting rules which potentially affect pre-existing tests
  • State gas accounting changes · Checklist revision 2 only
    New state gas accounting rules. State gas is the cost of *writing* state, as opposed to accessing or executing it: `StateGasCosts`, `COST_PER_STATE_BYTE`, the block-level state gas budget, and the spill path into execution gas.
  • New EVM gas refund
    New gas-refund mechanism

Blocks, transactions, and encoding

Transaction types and validity, block and header fields, encodings, syncing, and activation-time changes.

  • New transaction types
    Introduces a new transaction type
  • New or modified transaction validity mechanisms
    Creates new or modifies pre-existing transaction types' validation mechanisms
  • New block / header fields
    Introduces new block or block header fields
  • Encoding changes (RLP/SSZ)
    Introduces encoding changes at the transaction/block/interfaces level
  • Block syncing changes
    Modifies block RLP validation mechanisms that require test client syncing.
  • New fork activation mechanism
    Modifies state, internal variables, or similar, at the fork activation block

Client interfaces

Engine API and transition-tool interface changes.

  • Engine API changes
    Introduces new fields to the Engine API directives
  • Engine API encoding changes · Checklist revision 1 only
    Engine API encoding changes (the revision-1 template defines no anchor text for this row).
  • Transition-tool interface changes
    Modifies or adds new fields to the transition tool interface.

Testing impact

Rework, new invariants, and new primitives required in the test framework.

  • Patterns affecting pre-existing tests
    Implements a new validation mechanism or rule that translates in reworking pre-existing tests
  • New invariant on pre-existing tests · Checklist revision 2 only
    Tests that are **not about this EIP** must nonetheless assert something this EIP produces. Their logic does not change; they gain a new thing to check.
  • New test-framework primitives · Checklist revision 2 only
    Requires new abstractions in the test framework itself — expectation types, modifiers, helpers — beyond writing test functions with what already exists.

Risk and validation

Security, performance, boundary conditions, and cryptography that need validation.

  • Security risks
    Introduces or modifies mechanisms that could compromise the security of the chain, users, validators, or other stakeholders, if not implemented properly.
  • Performance risks
    Introduces or modifies mechanisms and requires performance validation.
  • Edge/boundary conditions
    Feature contains edge/boundary conditions.
  • Cryptography
    Introduces new cryptography mechanisms or modifies existing functionality that involves cryptography

Coordination

Cross-EIP interactions and behavior that clients must agree on before tests exist.

  • Cross-EIP interactions
    Introduces or modifies mechanisms that affect other EIPs in either the same or past forks.
  • Unspecified behavior requiring cross-client consensus · Checklist revision 2 only
    The EIP text does not determine the answer for cases a test can construct. Clients must agree on a previously unspecified detail before tests can be baselined. The cost here is coordination and re-baselining, not test writing.