whatmodel.sh / Gemini 2.0 Flash-Lite (001)
Gemini 2.0 Flash-Lite (001)
↗ share
+ contribute
Gemini 2.0 Flash-Lite (001) is a closed-weights language model from Google, released February 2025. Licence: proprietary.
Catalogue identity notes
Comparison-only. Stable Gemini API version gemini-2.0-flash-lite-001; Gemini API deprecations page (observed 2026-10-09): release date February 25, 2025, shutdown date June 1, 2026 (so no current API). Distinct from the catalogued gemini-2-0-flash-lite-preview-02-05. Appears in several ledger sources' multi-model runs: BFCL v3 (2025-06-14, result folder gemini-2.0-flash-lite-001-FC), Galileo Agent Leaderboard v1, SpeakLeash CPTUB, EuroEval and Open Persian LLM Leaderboard.
Model information sources
$ how it compares
The LLMs ranked either side of Gemini 2.0 Flash-Lite (001), out of 828 with a score, then more from Google.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 210 |  GPT-5 nano | 62±1 | api $0.14/M | ||
| 211 |  Qwen3-VL 32B Thinking | 62±1 | api $0.28/M +local | ||
| 212 | Gemini 2.0 Flash-Lite (001) | 62±2 | comparison only | ||
| 213 |  Mistral Large 3 (675B-A41B) | 62±1 | api $0.75/M +local | ||
| 214 |  Apriel 1.6 15B Thinker | 62±2 | local | ||
| more from Google | |||||
| 9 | Gemini 4 Argon (limited preview) | 82±1 | limited preview | ||
| 23 | Gemini 3.8 Flash | 77±1 | api $1.50/M | ||
| 32 | Gemini 3.7 Flash | 76±1 | api $1.50/M | ||
$ what it's good at
agent tasks▁▁▂▆█▆▅▄▄▃▂▁ #255 of 340 * · 10% of its score · 2 tests
Beats o3-mini here, though they rank higher overall. Trails SmolLM3 3B, Jamba 1.5 Mini, LFM2.5 1.2B Thinking here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| BFCL v3 | 56.2% ✎ | ▁▁▁▁▁▃▅█▅▄▁▁ beats 63/114 | 6.1% |
| Galileo Agent Leaderboard v1 (tool selection quality) | 93.3% ✎ | ▃▃▃▃▆▅▆▅█▂▅▂ beats 28/31 | 3.6% |
other tests13 not in a task · 89% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| AHELM Speech Robust Bench (LibriSpeech-clean with noise) transcription WER | 4.9% ✎ | ▂·█··▆▄·▂▂·▄ beats 12/13 | 28% |
| CPTUB average (SpeakLeash, 0-5 judge scale) | 81.9% ✎ | ▁▂▂▂▃█▃▆▅▄▂▃ beats 85/95 | 14% |
| Open Persian LLM Leaderboard v2 average (21 tasks) | 69.1% ✎ | ▂▄▂▃█▄▃▆▃▅▂▂ beats 71/81 | 11% |
| AHELM VoxCeleb2 same-speaker detection (exact match) | 52.7% ✎ | ▂·▂·▂█▂▄▄··▄ beats 4/13 | 8.3% |
| AHELM CoRe-Bench conversational audio reasoning (pseudo-exact match) | 73.7% ✎ | ▂·▄··▂▂·▄▂█▄ beats 8/13 | 7.5% |
| AHELM LibriSpeech transcription by audio LLMs (WER) | 4.9% ✎ | ▃···▃·█▃▅▃▅█ beats 10/13 | 5.8% |
| AHELM MUStARD audio sarcasm detection (exact match) | 66.1% ✎ | ▂·······▆█▆▆ beats 13/13 | 5.2% |
| Open PT-LLM Leaderboard average (9 Portuguese tasks) | 80.6% ✎ | ▃▁▁▁▁▁▁▁▂█▅▁ beats 262/276 | 4.4% |
5 more tests
| test | result | vs the others in its run | counts |
|---|---|---|---|
| AHELM AIR-Bench Foundation music subsets (exact match) | 64.1% ✎ | ▃█▃▅▃·▃·▃▅▃▃ beats 8/13 | 2.3% |
| AHELM MELD audio emotion classification (pseudo-exact match) | 36.8% ✎ | ▃··▃▃▃·▃▅▅█▅ beats 3/13 | 1.5% |
| AHELM FLEURS 7-language transcription by audio LLMs (WER) | 44.3% ✎ | ▄▂···▂▆▂█▂·▂ beats 11/13 | 0.9% |
| AHELM Multilingual LibriSpeech 7-language transcription by audio LLMs (WER) | 6.7% ✎ | ▂▂▂··▂▂·▂▂█▆ beats 10/13 | 0.1% |
| AHELM VocalSound human-sound recognition (prefix exact match) | 50.6% ✎ | ██▄▄·█·█·█▄▄ beats 3/13 | 0.0% |
$ where to run it
No verified API or download recorded yet · add one
$ how the score was worked out · AHELM: A Holistic Evaluation… 60%, SpeakLeash CPTUB (Complex Pol… 14%, Open Persian LLM Leaderboard… 11% and 3 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
| source | results | share of the score |
|---|---|---|
 AHELM: A Holistic Evaluation of Audio-Language Models (Stanford CRFM, arXiv:2508.21376v2) | 10 | 60% |
 SpeakLeash CPTUB (Complex Polish Text Understanding Benchmark) | 1 | 14% |
| Open Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab) | 1 | 11% |
| Berkeley Function Calling Leaderboard result archive | 1 | 6% |
| Open Portuguese LLM Leaderboard (archived) | 1 | 4% |
| Galileo Agent Leaderboard (v1 and v2 results) | 1 | 4% |
| prior · pull toward the middle | 1% | |
| weighted average | = 61.9 |
$ improve this page
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