SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.14033 · 2023

T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Step

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 0 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/2312.14033.json · badge: /api/ran/2312.14033.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
open-compass/t-eval canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
FunctionStatusWhere it lives
format_load Ran
ran; our contract draft was wrong, not the code
open-compass/t-eval/teval/utils/format_load.py
code served (permissive licence) · get_code("97c49c5e4a2bd446")
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 ast
import json

# Test case 1: Simple dictionary as string
raw_data_1 = "{'key': 'value', 'number': 42}"

# Test case 2: JSON formatted string
raw_data_2 = '{"name": "test", "items": [1, 2, 3]}'

# Test case 3: JSON with markdown code block
raw_data_3 = '```json\n{"data": "formatted"}\n```'

# Test case 4: With start and end characters
raw_data_4 = 'prefix {"config": true} suffix'

# Test case 5: Non-string input (should return as-is)
raw_data_5 = 12345

ARGS = {
    "raw_data": "{'key': 'value', 'number': 42}",
    "start_character": '',
    "end_character": ''
}
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
format_string Ran
ran; our contract draft was wrong, not the code
open-compass/t-eval/teval/utils/template.py
code served (permissive licence) · get_code("59c28643240aab3c")
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)

# Construct arguments for format_string function
template = "{who} like {what}"
input_data = {
    "who": "Alice",
    "what": "Python"
}

ARGS = {
    "template": template,
    "input_data": input_data
}
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
parse_string Ran
ran; our contract draft was wrong, not the code
open-compass/t-eval/teval/utils/template.py
code served (permissive licence) · get_code("8ef5a752e60695c5")
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 re
from string import Formatter

# Test case 1: Simple template matching
template1 = '{who} like {what}'
input_string1 = 'monkey like banana'

# Test case 2: Template with repeated keys
template2 = '{what} like {what}'
input_string2 = 'monkey like banana'

# Test case 3: Template with newlines allowed
template3 = '{greeting}\n{message}'
input_string3 = 'hello\nworld'

# Test case 4: Non-matching input
template4 = '{who} love {what}'
input_string4 = 'cat like fish'

ARGS = {
    'template': '{who} like {what}',
    'input_string': 'monkey like banana',
    'allow_newline': False
}
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

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 3 later) and 0 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
format_load 1 other paper
1 later
2024.acl-long.515 (2024 (year only))
T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Step
format_string 1 other paper
1 later
2024.acl-long.515 (2024 (year only))
T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Step
parse_string 1 other paper
1 later
2024.acl-long.515 (2024 (year only))
T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Step

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

Large language models (LLM) have achieved remarkable performance on various NLP tasks and are augmented by tools for broader applications. Yet, how to evaluate and analyze the tool-utilization capability of LLMs is still under-explored. In contrast to previous works that evaluate models holistically, we comprehensively decompose the tool utilization into multiple sub-processes, including instruction following, planning, reasoning, retrieval, understanding, and review. Based on that, we further introduce T-Eval to evaluate the tool utilization capability step by step. T-Eval disentangles the tool utilization evaluation into several sub-domains along model capabilities, facilitating the inner understanding of both holistic and isolated competency of LLMs. We conduct extensive experiments on T-Eval and in-depth analysis of various LLMs. T-Eval not only exhibits consistency with the outcome-oriented evaluation but also provides a more fine-grained analysis of the capabilities of LLMs, providing a new perspective in LLM evaluation on tool-utilization ability. The benchmark will be available at https://github.com/open-compass/T-Eval.

For agents

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

get_harvested_code_for_paper("2312.14033")
get_code_for_paper("2312.14033")
have("2312.14033")

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

curl https://syntology.ai/api/ran/2312.14033.json

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

[![Syntology run record](https://syntology.ai/api/ran/2312.14033.svg)](https://syntology.ai/paper/2312.14033)

Connect an agent — have() is free.