SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.04770 · 2024

WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild

arXiv · PDF · Open in the Atlas

Code that ran

5 of 9 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 4 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2406.04770.json · badge: /api/ran/2406.04770.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
allenai/wildbench canonical (classifier label)
classifier basis: census
5 ran · 4 no recorded run
FunctionStatusWhere it lives
clear_output Ran
ran; our contract draft was wrong, not the code
allenai/wildbench/src/unified_utils.py
code served (permissive licence) · get_code("bab78e56b3db5391")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

ARGS = {
    "output": "This is a sample text with <|endoftext|> and </s> and <pad> and <end_of_turn> tokens that need clearing.",
    "model_name": "gpt2"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
compute_single_round Ran
ran; our contract draft was wrong, not the code
allenai/wildbench/leaderboard/wb_elo.py
code served (permissive licence) · get_code("f835da725b875459")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import json
import random
from collections import defaultdict

# Create a minimal votes list with the required structure
votes = [
    {
        'model_1': 'gpt-4',
        'model_2': 'claude-3',
        'winner': 'gpt-4',
        'length_1': 150,
        'length_2': 120
    },
    {
        'model_1': 'llama-2',
        'model_2': 'gpt-4',
        'winner': 'tie',
        'length_1': 200,
        'length_2': 195
    },
    {
        'model_1': 'claude-3',
        'model_2': 'llama-2',
        'winner': 'claude-3',
        'length_1': 100,
        'length_2': 180
    },
]

# Create initial elos dict
init_elos = {
    'gpt-4': 1200,
    'claude-3': 1100,
}

ARGS = {
    'votes': votes,
    'K': 32,
    'init_elos': init_elos,
    'dynamic': True,
    'interval': 10,
    'use_regressed_as_init': False,
    'length_margin': -1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
formatter Ran
ran, honoured the contract we drafted
allenai/wildbench/leaderboard/data_utils.py
code served (permissive licence) · get_code("e6e6e2172255fa63")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned float, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

ARGS = {
    "x": 3.14159
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_all_votes Ran
ran, honoured the contract we drafted
allenai/wildbench/leaderboard/wb_elo.py
code served (permissive licence) · get_code("ad6c9f4f8fa20c1c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Set up global state that the function uses
all_scores_by_id_model = {
    'session_1': {
        'model_a': 8.5,
        'model_b': 6.2,
        'model_c': 7.1,
    },
    'session_2': {
        'model_a': 9.0,
        'model_b': 8.5,
    }
}

all_outputs_by_id_model = {
    'session_1': {
        'model_a': 'This is a valid output from model a',
        'model_b': 'This is model b output',
        'model_c': 'Model c generated this response',
    },
    'session_2': {
        'model_a': 'Another output from model a with more content here',
        'model_b': 'Model b response text',
    }
}

ARGS = {
    'margin': 2,
    'tie_margin': 1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
sanitize_args Ran
ran; our contract draft was wrong, not the code
allenai/wildbench/src/unified_infer.py
code served (permissive licence) · get_code("8526e7d6eb6a6bd3")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Args. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import argparse

# Create a simple namespace object to act as args
class Args:
    def __init__(self):
        self.download_dir = 'default'

args = Args()

ARGS = {
    'args': args
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Args — a Args output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Args output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
compute_elo_based_on_votes Not yet run
unverified (harvested, no recorded run)
allenai/wildbench/leaderboard/wb_elo.py
code served (permissive licence) · get_code("55f88619b89a0830")
How it ran

no invocation recorded.

get_conv_template Not yet run
unverified (harvested, no recorded run)
allenai/wildbench/src/fastchat_conversation.py
code served (permissive licence) · get_code("2e17447aecaa3b2e")
How it ran

no invocation recorded.

load_infer_results Not yet run
unverified (harvested, no recorded run)
allenai/wildbench/leaderboard/data_utils.py
code served (permissive licence) · get_code("6228967ca49853d1")
How it ran

no invocation recorded.

sample_an_eval_result Not yet run
unverified (harvested, no recorded run)
allenai/wildbench/leaderboard/data_utils.py
code served (permissive licence) · get_code("3ea3d1a085a300ea")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 7 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 2 the same month, 7 later) and 2 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
get_conv_template 69 other papers
28 dated earlier, 8 the same month, 28 later, 4 same year, order not determinable, 1 undated
1911.03705 (2019-11)
CommonGen: A Constrained Text Generation Challenge for Generative Commonsense Reasoning
2112.05682 (2021-12)
Self-attention Does Not Need $O(n^2)$ Memory
2204.07705 (2022-04)
SUPER-NATURALINSTRUCTIONS: Generalization via Declarative Instructions on 1600+ NLP Tasks
and 66 more not named here
sanitize_args 3 other papers
1 the same month, 2 later
2406.04127 (2024-06)
Are We Done with MMLU?
2408.14774 (2024-08)
Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning
2608.06310 (2026-08)
RRC: Unlocking Generative Reward Models in LLM Reinforcement Learning via Ranking-Based Reward Construction
clear_output 1 other paper
1 later
2608.06310 (2026-08)
RRC: Unlocking Generative Reward Models in LLM Reinforcement Learning via Ranking-Based Reward Construction
compute_elo_based_on_votes 1 other paper
1 later
2608.06310 (2026-08)
RRC: Unlocking Generative Reward Models in LLM Reinforcement Learning via Ranking-Based Reward Construction
compute_single_round 1 other paper
1 later
2608.06310 (2026-08)
RRC: Unlocking Generative Reward Models in LLM Reinforcement Learning via Ranking-Based Reward Construction
formatter 1 other paper
1 later
2608.06310 (2026-08)
RRC: Unlocking Generative Reward Models in LLM Reinforcement Learning via Ranking-Based Reward Construction
get_all_votes 1 other paper
1 later
2608.06310 (2026-08)
RRC: Unlocking Generative Reward Models in LLM Reinforcement Learning via Ranking-Based Reward Construction

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We introduce WildBench, an automated evaluation framework designed to benchmark large language models (LLMs) using challenging, real-world user queries. WildBench consists of 1,024 tasks carefully selected from over one million human-chatbot conversation logs. For automated evaluation with WildBench, we have developed two metrics, WB-Reward and WB-Score, which are computable using advanced LLMs such as GPT-4-turbo. WildBench evaluation uses task-specific checklists to evaluate model outputs systematically and provides structured explanations that justify the scores and comparisons, resulting in more reliable and interpretable automatic judgments. WB-Reward employs fine-grained pairwise comparisons between model responses, generating five potential outcomes: much better, slightly better, slightly worse, much worse, or a tie. Unlike previous evaluations that employed a single baseline model, we selected three baseline models at varying performance levels to ensure a comprehensive pairwise evaluation. Additionally, we propose a simple method to mitigate length bias, by converting outcomes of ``slightly better/worse'' to ``tie'' if the winner response exceeds the loser one by more than $K$ characters. WB-Score evaluates the quality of model outputs individually, making it a fast and cost-efficient evaluation metric. WildBench results demonstrate a strong correlation with the human-voted Elo ratings from Chatbot Arena on hard tasks. Specifically, WB-Reward achieves a Pearson correlation of 0.98 with top-ranking models. Additionally, WB-Score reaches 0.95, surpassing both ArenaHard's 0.91 and AlpacaEval2.0's 0.89 for length-controlled win rates, as well as the 0.87 for regular win rates.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2406.04770")
get_code_for_paper("2406.04770")
have("2406.04770")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2406.04770.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2406.04770.svg)](https://syntology.ai/paper/2406.04770)

Connect an agent — have() is free.