whatmodel.sh / Gemini 2.0 Flash (001)

Gemini 2.0 Flash (001)

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Gemini 2.0 Flash (001) is a closed-weights language model from Google, released February 2025. Licence: proprietary.

Catalogue identity notes

Comparison model from the Epoch AI internal-evaluation CSVs (Epoch release date 2025-02-05). Stable API version gemini-2.0-flash-001. Gemini API deprecations page: shutdown date June 1, 2026.

60.0±1.0comparison only: no current run option verifiedfrom 25 benchmark results across 13 sources

$ how it compares

The LLMs ranked either side of Gemini 2.0 Flash (001), out of 828 with a score, then more from Google.

#modelscorewhereRAMreleased
232Qwen3-VL 32B Instruct Alibaba60±1api $0.28/M +local~22GB2025-10
233Falcon-H1R 7B TII60±1local~6GB2026-01
234Gemini 2.0 Flash (001) Google60±1comparison only2025-02
235ERNIE 4.5 300B-A47B Baidu60±1local~97GB2025-06
236Mistral Medium 3 (2505) Mistral60±1comparison only2025-05
more from Google
9Gemini 4 Argon (limited preview) Google82±1limited preview2026-09
23Gemini 3.8 Flash Google77±1api $1.50/M2026-09
32Gemini 3.7 Flash Google76±1api $1.50/M2026-08

see all LLMs · find the ones that fit your machine

$ what it's good at

agent tasks▁▁▂▆█▆▅▄▄▃▂▁ #224 of 340 · 8.0% of its score · 3 tests

Beats o1 (2024-12-17), o3-mini, DeepSeek R1 (Jan '25) here, though they rank higher overall. Trails SmolLM3 3B, Jamba 1.5 Mini, Mellum2 12B-A2.5B Instruct here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Finance Agent Benchmark v1 (537 questions, class-balanced accuracy)14.4% ✎█·▃▃·█▅▅▅▅▃▅ beats 9/18very hard · avg 5.8%▇▇ 5.1%sharp
BFCL v361.2% ✎▁▁▁▁▁▃▅█▅▄▁▁ beats 84/114medium · avg 52%▇ 1.8%blunt · at its level
Galileo Agent Leaderboard v1 (tool selection quality)93.8% ✎▃▃▃▃▆▅▆▅█▂▅▂ beats 29/31easy · avg 79%▇ 1.1%blunt
chat & writing▁▁▁▃▅▄▆█▇▇▇▃ #174 of 463 * · 8.5% of its score · 1 test

Beats INTELLECT-3, MiniMax-M2, MiniCPM5 2B here, though they rank higher overall. Trails LFM2.5 1.2B Thinking, LFM2.5 8B-A1B, LFM2.5 2.6B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
LMArena (text)1359.9 ✎▁▁▁▂▃▃▃▆▆▇█▃ beats 203/379avg 1268▇▇▇ 8.5%blunt
math▁▂▃▅▇▅▅█▄▁▁▁ #204 of 462 * · 24% of its score · 2 tests

Beats MiniMax-M2.1, DeepSeek V3 0324 here, though they rank higher overall. Trails Phi-4-mini-reasoning 3.8B, OpenThinker3 7B, Olmo 3 7B Think here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
MATH level 582.2% ✎▂▂▅▆▄█▆▃▅▂▃▄ beats 68/92hard · avg 32%▇▇▇▇▇▇ 15%sharp
OTIS mock AIME 2024–202531.1% ✎▃▃▄▃▃▃▇▇█▃▂▅ beats 67/193very hard · avg 8.5%▇▇▇ 8.7%sharp · at its level · noisy
vision & documents▁▁▃▃▂▃▅▄▇▇█▃ #104 of 182 * · 5.9% of its score · 1 test

Beats DeepSeek V4 Flash Vision (Exp), GLM-4.6V, GPT-5 nano here, though they rank higher overall. Trails Mistral Small 4 (119B-A6.5B) here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Arena vision (style controlled)1171.9 ✎▁▁▂▂▂▂▄▅▅▆██ beats 58/145avg 1068▇▇ 5.9%blunt
web search▂·▂▇▅█▃▄▃▂▁▁ #10 of 92 * · 5.1% of its score · 1 test

Beats GPT-6 Astra, Claude Opus 5.5, Claude Fable 5.1 here, though they rank higher overall. Trails GPT-4o (2024-08-06) here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Finance Agent Benchmark v1 (537 questions, class-balanced accuracy)14.4% ✎█·▃▃·█▅▅▅▅▃▅ beats 9/18very hard · avg 5.8%▇▇ 5.1%sharp
other tests18 not in a task · 54% of its score
testresultvs the others in its rundifficultycountswhy
GPQA Diamond64.1% ✎▁▁▁▁▂▄▆▄▅▇█▅ beats 92/208hard · avg 40%▇▇▇▇▇▇ 16%sharp · at its level
AHELM Speech Robust Bench (LibriSpeech-clean with noise) transcription WER17.8% ✎▂·█··▆▄·▂▂·▄ beats 8/13avg 33%▇▇▇ 8.0%typical
EQ-Bench 3 (emotional intelligence, judge Elo)1096.6 ✎▁·▂▁▄▅▅▃█▄▁▁ beats 12/62avg 1044▇▇ 5.2%typical
BRIDGE clinical text, zero-shot average (87 tasks)43.0% ✎▁▁▁▁▁▂▂▃▄▆█▃ beats 88/97hard · avg 32%▇▇ 4.7%blunt · at its level
CPTUB average (SpeakLeash, 0-5 judge scale)85.8% ✎▁▂▂▂▃█▃▆▅▄▂▃ beats 90/95easy · avg 66%▇▇ 4.3%typical
Open Persian LLM Leaderboard v2 average (21 tasks)73.8% ✎▂▄▂▃█▄▃▆▃▅▃▂ beats 77/81medium · avg 58%▇ 3.2%blunt · at its level
AHELM CoRe-Bench conversational audio reasoning (pseudo-exact match)75.6% ✎▂·▄··▂▂·▄▂█▄ beats 10/13medium · avg 53%▇ 2.3%at its level
AHELM VoxCeleb2 same-speaker detection (exact match)52.9% ✎▂·▂·▂█▂▄▄··▄ beats 5/13very hard · avg 54%▇ 2.1%sharp · noisy
10 more tests
testresultvs the others in its rundifficultycountswhy
DiagnosticIQ industrial maintenance MCQ (macro accuracy, 4 options)57.6% ✎▁··▃▁▁▁▅█▅▁▅ beats 7/24medium · avg 52%▇ 1.7%blunt · at its level
AHELM LibriSpeech transcription by audio LLMs (WER)4.3% ✎▃···▃·█▃▅▃▅█ beats 12/13avg 11%▇ 1.7%blunt
AHELM MUStARD audio sarcasm detection (exact match)60.4% ✎▂·······▆█▆▆ beats 9/13very hard · avg 57%▇ 1.4%blunt
Open PT-LLM Leaderboard average (9 Portuguese tasks)82.3% ✎▃▁▁▁▁▁▁▁▂█▅▃ beats 268/276medium · avg 73%▇ 1.4%noisy
AHELM AIR-Bench Foundation music subsets (exact match)69.7% ✎▃█▃▅▃·▃·▃▅▃▃ beats 10/13medium · avg 57%▇ 0.7%blunt · at its level
AHELM MELD audio emotion classification (pseudo-exact match)42.3% ✎▃··▃▃▃·▃▅▅█▅ beats 4/13medium · avg 40%▇ 0.4%blunt · at its level
Vectara hallucination leaderboard, 2025 dataset (HHEM-2.3, factual consistency rate)99.3% ✎▁▁▂▃▄▄█▆▃▂▂▃ beats 140/140very easy · avg 94%▇ 0.3%blunt · maxed out · noisy
AHELM FLEURS 7-language transcription by audio LLMs (WER)64.8% ✎▄▂···▂▆▂█▂·▂ beats 5/13avg 80%▇ 0.3%blunt · noisy
AHELM Multilingual LibriSpeech 7-language transcription by audio LLMs (WER)6.0% ✎▂▂▂··▂▂·▂▂█▆ beats 12/13avg 13%▇ 0.0%blunt · noisy
AHELM VocalSound human-sound recognition (prefix exact match)71.9% ✎██▄▄·█·█·█▄▄ beats 7/13easy · avg 67%▇ 0.0%blunt · at its level · noisy

$ where to run it

No verified API or download recorded yet · add one

$ how the score was worked out · Epoch AI — internal evaluatio… 39%, AHELM: A Holistic Evaluation… 17%, LMArena leaderboard dataset 14% and 10 more

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
Epoch AI — internal evaluations3▇▇▇▇▇▇▇▇▇▇▇▇ 39%CC BY 4.0
AHELM: A Holistic Evaluation of Audio-Language Models (Stanford CRFM, arXiv:2508.21376v2)10▇▇▇▇▇ 17%CC BY 4.0
LMArena leaderboard dataset2▇▇▇▇ 14%CC BY 4.0
EQ-Bench 3 canonical leaderboard results1▇▇ 5%MIT
Finance Agent Benchmark (Vals AI, arXiv:2508.00828v1)1▇▇ 5%CC-BY-4.0
BRIDGE Medical Leaderboard (Harvard Medical School / Brigham and Women's YLab)1▇ 5%MIT
SpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)1▇ 4%MIT
Open Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab)1▇ 3%Apache-2.0
Berkeley Function Calling Leaderboard result archive1▇ 2%Apache-2.0
DiagnosticIQ: A Benchmark for LLM-Based Industrial Maintenance Action Recommendation from Symbolic Rules (arXiv:2605.08614v1)1▇ 2%CC BY 4.0
Open Portuguese LLM Leaderboard (archived)1▇ 1%Apache-2.0
Galileo Agent Leaderboard (v1 and v2 results)1▇ 1%Apache-2.0
Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository)1▇ 0%Apache-2.0
prior · pull toward the middle▇ 0%
weighted average= 60.0

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json