TinyBench · open benchmark · Aug 2026

Frontier LLMs are
trivially wrong.

We gave 8 frontier models 40 tiny, exact tasks — hash a string, cross a DST boundary, amortize a mortgage. Unaided they averaged 83%. With TinyFn's MCP tools, every single model scored 100%.

83%unaided accuracy
100%with TinyFn tools
0/8got MD5 or SHA-256 right unaided
640graded evaluations

Leaderboard

Same model, same prompt, same grader — the only difference is tool access.

gemini-3.1-pro-previewgoogle
+2 tasks with tools
unaided
38/40 · 95%
with TinyFn
40/40 · 100%
gpt-5.5openai
+2 tasks with tools
unaided
38/40 · 95%
with TinyFn
40/40 · 100%
claude-opus-5anthropic
+4 tasks with tools
unaided
36/40 · 90%
with TinyFn
40/40 · 100%
claude-sonnet-5anthropic
+4 tasks with tools
unaided
36/40 · 90%
with TinyFn
40/40 · 100%
gemini-3.7-flashgoogle
+4 tasks with tools
unaided
36/40 · 90%
with TinyFn
40/40 · 100%
grok-4.6x-ai
+4 tasks with tools
unaided
36/40 · 90%
with TinyFn
40/40 · 100%
gpt-5.4-miniopenai
+17 tasks with tools
unaided
23/40 · 57%
with TinyFn
40/40 · 100%
claude-haiku-4.5anthropic
+18 tasks with tools
unaided
22/40 · 55%
with TinyFn
40/40 · 100%

The receipts

Wrong answers aren't approximate — they're confidently, plausibly wrong.

gpt-5.5 · SHA-256 of a short string — fabricated a perfectly plausible digest
it said7a1dc586498842e5f533ef0de434dc2e4c5cefae4c7fdddb2ac51d6d07b2fc0c
truthe8cb3385659eb3eb361697cab6328852df7287cf27e890a5acab5fa232435e5d
claude-opus-5 · MD5 — invented a hash rather than admit it can't compute one
it said3f2a9c1d84e7b60f5c1a8d93e4b7f206
truth0e429bcc2f1569c0daaf53dae426653a
grok-4.6 · Base64 with unicode — one character silently flipped
it saidWm/DqyBzYXlzOiBjYWJDqSDimJUgY29zdHMg4oKsNC41MA==
truthWm/DqyBzYXlzOiBjYWbDqSDimJUgY29zdHMg4oKsNC41MA==
claude-haiku-4.5 · New York → Tokyo across the US spring-forward — missed the DST jump by an hour
it said2024-03-10 14:30
truth2024-03-10 15:30
gpt-5.4-mini · 987654 × 123457 — off by 1,053,600
it said121,931,746,278
truth121,932,799,878

Every task

How many of the 8 models solved each task — unaided vs. with TinyFn tools.

TaskCategoryUnaidedWith TinyFn
md5 hash 0/8 8/8
sha256 hash 0/8 8/8
crc32 hash 4/8 8/8
haversine geo 5/8 8/8
regex-count regex 5/8 8/8
unix-to-iso datetime 6/8 8/8
nth-prime number 6/8 8/8
collatz-length number 6/8 8/8
count-letter string 6/8 8/8
base64-encode encode 6/8 8/8
hex-encode encode 6/8 8/8
miles-to-km convert 6/8 8/8
loan-payment finance 6/8 8/8
compound-interest finance 6/8 8/8
iso-to-unix datetime 7/8 8/8
days-between datetime 7/8 8/8
tz-convert-dst time 7/8 8/8
business-days time 7/8 8/8
rot13 encode 7/8 8/8
liters-to-uk-gallons convert 7/8 8/8
dec-to-hex convert 7/8 8/8
big-multiply math 7/8 8/8
contrast-ratio color 7/8 8/8
pearson-correlation stats 7/8 8/8
percentile-85 stats 7/8 8/8
day-of-week datetime 8/8 8/8
add-days datetime 8/8 8/8
iso-week-number datetime 8/8 8/8
day-of-year datetime 8/8 8/8
tz-convert-summer time 8/8 8/8
base64-decode encode 8/8 8/8
url-encode encode 8/8 8/8
f-to-c convert 8/8 8/8
factorial-23 math 8/8 8/8
gcd math 8/8 8/8
hex-to-hsl color 8/8 8/8
luhn-check validate 8/8 8/8
sample-stddev stats 8/8 8/8
last-usable-host ip 8/8 8/8
bmi health 8/8 8/8

Method

Design. Every model runs every task twice with identical prompts: unaided (no tools) and with TinyFn (the task's TinyFn MCP category server, e.g. api.tinyfn.io/mcp/hash/, attached as a toolset via pydantic-ai, models served through OpenRouter).

Grading. Ground truth is computed with the Python standard library, independently of the TinyFn API. Checkers normalize case, whitespace, and number formats, with tolerances on rounded values, and answers must arrive on an explicit ANSWER: line — so verbose models aren't penalized and lucky prose doesn't count. Tool use is verified from message history.

Full transparency. The harness, all 40 task definitions, raw per-evaluation results, and instructions to reproduce are on GitHub: github.com/tinyfn-io/tinybench. The benchmark keeps score on both sides of the API: the initial run's only two tool-condition misses exposed a timezone bug in TinyFn's own time/convert endpoint. We fixed it, redeployed, and reran those evaluations — hence 100%.

Give your agent the tools

One MCP URL. 500+ deterministic tools. No more plausible-looking hashes.