Benchmark Almanac

FiQA SA (BloombergGPT protocol)

FinGPT v3.0.1 (openai) 0.89 tops its leaderboard GPT-4 Jun 2023 0.63 leads the models we track
Not in model cards

Models classify sentiment toward a named financial target as negative, neutral, or positive. Bloomberg uses five examples and reports weighted F1.

FinGPT independently ran the three-class task. Its authors could not reproduce Bloomberg’s exact split. Bloomberg reports 235 test sentences. AdaptLLM also releases 235 examples with different label counts.

Made by
Bloomberg
Released
March 2023
Kind
Finance
Level
Everyday
Scored
Checked automatically
Answers
Multiple choice
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Text
Interaction
Single turn
Items from
Another benchmark
Refresh
One fixed set
Run by
Anyone
In views
Law and finance
Strongest model tested
GPT-4 Jun 2023 #186 on the capability index
Last model added
June 2023
Scores refreshed
November 20th, 2026
14
Entries on its own leaderboard, 1 model we track

FinGPT v3.0.1 (openai) tops the leaderboard with 0.89 GPT-4 leads with 0.63

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is GPT-4, at 0.63. This view shows only models we track, each at its best.

  1. 1 FinGPT v3.0.1 (openai) 0.89
  2. 2 FinGPT v3.3 0.87
  3. 3 FinGPT v3.2 0.86
  4. 4 FinGPT v3.1 0.85
  5. 5 FinGPT v3.1.1 (8bit) 0.85
  6. 6 FinGPT v.3.0.2 (FinBERT) 0.83
  7. 7 Llama2 0.80
  8. 8 ChatGLM2 0.79
  9. 9 FinGPT v3 0.76
  10. 10 FinGPT v3.1.2 (QLoRA) 0.75
  11. 11 BloombergGPT 0.75
  12. 12 ChatGPT 0.73
  13. 13 GPT-4 Jun 2023 0.63
  14. 14 FinBERT 0.60

Source: Official FiQA SA (BloombergGPT protocol) leaderboard

Source: Official FiQA SA (BloombergGPT protocol) leaderboard

#EntryScoreSettingDateSource
1 FinGPT v3.0.1 (openai) 0.89 Official leaderboard
2 FinGPT v3.3 0.87 Official leaderboard
3 FinGPT v3.2 0.86 Official leaderboard
4 FinGPT v3.1 0.85 Official leaderboard
5 FinGPT v3.1.1 (8bit) 0.85 Official leaderboard
6 FinGPT v.3.0.2 (FinBERT) 0.83 Official leaderboard
7 Llama2 0.80 Official leaderboard
8 ChatGLM2 0.79 Official leaderboard
9 FinGPT v3 0.76 Official leaderboard
10 FinGPT v3.1.2 (QLoRA) 0.75 Official leaderboard
11 BloombergGPT 0.75 Official leaderboard
12 ChatGPT 0.73 Official leaderboard
13 GPT-4 Jun 2023 0.63 Jun 2023 Official leaderboard
14 FinBERT 0.60 Official leaderboard
#ModelScoreSettingDateSource
1 GPT-4 Jun 2023 0.63 Jun 2023 Official leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard
0.63 2023 0.63 2023

Source: Official FiQA SA (BloombergGPT protocol) leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Law, finance and medicine

All 637 in Law, finance and medicine
  • MedXpertQA-MM In use Models answer expert-level medical exam questions that combine images with clinical records and test results. Scoring is accuracy. Qwen 3.8 Max 80.4%
  • HealthBench Professional In use 525 physician-authored tasks from real clinician chats (care consult, documentation, research) with physician-adjudicated rubrics. Claude Sonnet 5.5 69.2%
  • HealthBench In use 5,000 realistic health conversations graded against physician-written rubrics. A length-adjusted variant penalizes verbosity. GPT-5 67.2%
  • FinSearchComp In use Agents search the web to fetch live financial data, look up history, and run multi-step investigations, across 635 expert-written questions. Scored by answer accuracy. Ling-3.1-flash 81.7%
  • KorMedMCQA In use Models answer 7,469 multiple-choice questions from Korean licensing exams for doctors, nurses, pharmacists and dentists, held from 2012 to 2024. o1-preview 92.7%
  • Harvey LAB-AA v1.1 In use Artificial Analysis's run of Harvey's Legal Agent Benchmark on Harvey's newer private set of 120 tasks across 24 practice areas. A deliverable with a material hallucination scores zero, and the headline is the share of judges who find every rubric criterion passed. GPT-6.2 Astra 15%

Data audit

8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 3 years ago, in June 2023, for GPT-4. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (14 entries).
  • Pass Models scored 1 model we track, plus 13 other entries on its leaderboard.
  • Warning Newest score The newest came 3 years ago, in June 2023, for GPT-4.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-4 (#186).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on github.com: 1 row for models we track and 13 other entries at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check