# DAYJOB leaderboard

external benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/leaderboards/benchmarks/external-dayjob

Every model the catalog carries a published DAYJOB value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | external |
| Measure | Agent deliverables graded all-or-nothing against expert rubrics |
| Tasks | 130 long-horizon tasks: 80 finance and 50 healthcare |
| Difficulty | Long-horizon professional work |
| Published by | [BenchLM](https://benchlm.ai/benchmarks/dayjob) |

DAYJOB is Surge AI's test of long professional assignments: 80 finance tasks and 50 healthcare tasks that an agent must finish to an expert checklist. This is the combined 130-task board on Kaggle.

## DAYJOB ranking

19 models with a published DAYJOB value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Agent deliverables graded all-or-nothing against expert rubrics | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Claude Opus 5.5](https://modelchoice.dev/models/claude-opus-5-5) | Anthropic | 24.5 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Claude Sonnet 5.5](https://modelchoice.dev/models/claude-sonnet-5-5) | Anthropic | 21.7 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Gemini 4 Carbon](https://modelchoice.dev/models/gemini-4-carbon) | Google | 19.7 | Observed 2026-11-21 · source benchlm:models |
| 4 | [GPT-6 Astra](https://modelchoice.dev/models/gpt-6-astra) | OpenAI | 17.4 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Gemini 4 Argon](https://modelchoice.dev/models/gemini-4-argon) | Google | 15.7 | Observed 2026-11-21 · source benchlm:models |
| 6 | [GPT-6.1 Sol](https://modelchoice.dev/models/gpt-6-1-sol) | OpenAI | 15.5 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Claude Opus 5](https://modelchoice.dev/models/claude-opus-5) | Anthropic | 11.7 | Observed 2026-11-21 · source benchlm:models |
| 8 | [GPT-6 Sol](https://modelchoice.dev/models/gpt-6-sol) | OpenAI | 6.8 | Observed 2026-11-21 · source benchlm:models |
| 9 | [GPT-5.6 Sol](https://modelchoice.dev/models/gpt-5-6-sol) | OpenAI | 4.2 | Observed 2026-11-21 · source benchlm:models |
| 10 | [GPT-5.6 Terra](https://modelchoice.dev/models/gpt-5-6-terra) | OpenAI | 2.8 | Observed 2026-11-21 · source benchlm:models |
| 11 | [Gemini 3.8 Flash](https://modelchoice.dev/models/gemini-3-8-flash) | Google | 2.6 | Observed 2026-11-21 · source benchlm:models |
| 12 | [Claude Opus 4.8](https://modelchoice.dev/models/claude-opus-4-8) | Anthropic | 2.0 | Observed 2026-11-21 · source benchlm:models |
| 13 | [Claude Sonnet 5](https://modelchoice.dev/models/claude-sonnet-5) | Anthropic | 1.7 | Observed 2026-11-21 · source benchlm:models |
| 14 | [GPT-5.5](https://modelchoice.dev/models/gpt-5-5) | OpenAI | 1.4 | Observed 2026-11-21 · source benchlm:models |
| 15 | [GPT-6 Luna](https://modelchoice.dev/models/gpt-6-luna) | OpenAI | 1.2 | Observed 2026-11-21 · source benchlm:models |
| 16 | [GPT-5.6 Luna](https://modelchoice.dev/models/gpt-5-6-luna) | OpenAI | 1.1 | Observed 2026-11-21 · source benchlm:models |
| 17 | [Gemini 3 Flash](https://modelchoice.dev/models/gemini-3-flash) | Google | 0.0 | Observed 2026-11-21 · source benchlm:models |
| 17 | [Gemini 3.1 Pro](https://modelchoice.dev/models/gemini-3-1-pro) | Google | 0.0 | Observed 2026-11-21 · source benchlm:models |
| 17 | [Gemini 3.5 Flash-Lite](https://modelchoice.dev/models/gemini-3-5-flash-lite) | Google | 0.0 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
