# Gemini 2.5 Flash Lite

> Source: Benchize (https://benchize.com) — https://benchize.com/models/gemini-2-5-flash-lite. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/gemini-2-5-flash-lite.

Google

Canonical URL: https://benchize.com/models/gemini-2-5-flash-lite
Last updated: Thu, 22 Oct 2026 04:30:12 GMT

Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations.

Google

## Benchmarks

| Benchmark | Score | ± | Rank | Cost | Latency | Source |  |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [MedScribe / overall](https://benchize.com/benchmarks/vals-ai%3Amedscribe%3Aoverall.md) | 72.83% | SE ±1.98 pp | 40 / 49 | $0.00121 | 4.85source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 72.832 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.001211 \| USD \| per_test \| Lower is better \| \| `latency` \| 4.847 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Google reasoning Not reported Reasoning effort unknown Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.98 pp sourcePopulation 109 stderr 1.982 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medscribe.BYf5a3C-.json) Source Vals AI Original model label google/gemini-2.5-flash-lite Source version 1 Observed 2026-10-22T02:10:15.398Z Evidence SHA-256 `271fc122ddc2b0602bd6c7947f65a9a7f0d8cab94f6dc27d62a9380a9317f9c0` Source locator `/tasks/overall/google~1gemini-2.5-flash-lite` |  |  |  |  |  |  |  |
| [SAGE / PDEs](https://benchize.com/benchmarks/vals-ai%3Asage%3APDEs.md) | 20.64% | SE ±5.08 pp | 39 / 41 | $0.00112 | 12.78source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 20.635 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.001121 \| USD \| per_test \| Lower is better \| \| `latency` \| 12.776 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Google reasoning Not reported Reasoning effort unknown Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.08 pp sourcePopulation 91 stderr 5.078 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label google/gemini-2.5-flash-lite Source version 1 Observed 2026-10-22T02:10:22.165Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/PDEs/google~1gemini-2.5-flash-lite` |  |  |  |  |  |  |  |
| [NC Bench](https://benchize.com/benchmarks/nc-bench%3Aoverall.md) | 79.91% | — | 129 / 144 | — | — | [nc bench](https://www.nc-bench.com/models) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 79.91 \| percent \| reported \| Higher is better \| \| `tooling` \| 96 \| percent \| category \| Higher is better \| \| `creative_writing` \| 75.05 \| percent \| category \| Higher is better \| \| `language` \| 82.75 \| percent \| category \| Higher is better \| \| `utility` \| 80.14 \| percent \| category \| Higher is better \| \| `reasoning` \| 65.19 \| percent \| category \| Higher is better \| \| `text_editing` \| 92.13 \| percent \| category \| Higher is better \| \| `rule_following` \| 59.96 \| percent \| category \| Higher is better \| \| `hallucination` \| 88.08 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Gemini 2.5 Flash Lite thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Gemini 2.5 Flash Lite Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/169` |  |  |  |  |  |  |  |
| [SAGE / automata](https://benchize.com/benchmarks/vals-ai%3Asage%3Aautomata.md) | 33.33% | SE ±6.02 pp | 29 / 41 | $0.000876 | 10.45source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 33.334 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.000876 \| USD \| per_test \| Lower is better \| \| `latency` \| 10.448 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Google reasoning Not reported Reasoning effort unknown Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.02 pp sourcePopulation 91 stderr 6.023 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label google/gemini-2.5-flash-lite Source version 1 Observed 2026-10-22T02:10:22.165Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/google~1gemini-2.5-flash-lite` |  |  |  |  |  |  |  |
| [SAGE / linear algebra](https://benchize.com/benchmarks/vals-ai%3Asage%3Alinear_algebra.md) | 28.63% | SE ±5.08 pp | 41 / 41 | $0.000791 | 18.12source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 28.629 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.000791 \| USD \| per_test \| Lower is better \| \| `latency` \| 18.12 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Google reasoning Not reported Reasoning effort unknown Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.08 pp sourcePopulation 91 stderr 5.077 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label google/gemini-2.5-flash-lite Source version 1 Observed 2026-10-22T02:10:22.165Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/linear_algebra/google~1gemini-2.5-flash-lite` |  |  |  |  |  |  |  |
| [SAGE / calculus](https://benchize.com/benchmarks/vals-ai%3Asage%3Acalculus.md) | 13.89% | SE ±4.3 pp | 32 / 36 | $0.0017 | 13.34source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 13.889 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.001699 \| USD \| per_test \| Lower is better \| \| `latency` \| 13.337 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Google reasoning Not reported Reasoning effort unknown Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.3 pp sourcePopulation 91 stderr 4.298 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label google/gemini-2.5-flash-lite Source version 1 Observed 2026-10-22T02:10:22.165Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/calculus/google~1gemini-2.5-flash-lite` |  |  |  |  |  |  |  |
| [MedCode / overall](https://benchize.com/benchmarks/vals-ai%3Amedcode%3Aoverall.md) | 27.12% | SE ±1.84 pp | 45 / 49 | $0.00134 | 5.75source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_medcode.DehpEDgG.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 27.115 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.001342 \| USD \| per_test \| Lower is better \| \| `latency` \| 5.746 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Google reasoning Not reported Reasoning effort unknown Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.84 pp sourcePopulation 107 stderr 1.843 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_medcode.DehpEDgG.json) Source Vals AI Original model label google/gemini-2.5-flash-lite Source version 1 Observed 2026-10-22T02:10:14.899Z Evidence SHA-256 `988a6ae1e07e33ce031572ed4a804be11c36ee97a1dd75cbe4740fff3b534f8c` Source locator `/tasks/overall/google~1gemini-2.5-flash-lite` |  |  |  |  |  |  |  |
| [Berkeley Function Calling Leaderboard](https://benchize.com/benchmarks/bfcl%3Aoverall.md) | 36.87% | — | 15 / 26 | $7.55 | 1.18s | [Berkeley Function Calling Leaderboard](https://api.github.com/repos/HuanzhiMao/BFCL-Result/contents/2025-12-16/score/data_overall.csv?ref=cadd76a8dc62984e7bf15ecaf358f070bae745cc) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 36.87 \| percent \| reported \| Higher is better \| \| `cost_total` \| 7.55 \| USD \| evaluation_total \| Lower is better \| \| `latency_mean` \| 1.18 \| seconds \| per_call_mean \| Lower is better \| \| `latency_sd` \| 8.06 \| seconds \| per_call_sd \| Lower is better \| \| `non_live_ast_acc` \| 86.6 \| percent \| reported_task_score \| Higher is better \| \| `non_live_simple_ast` \| 70.92 \| percent \| reported_task_score \| Higher is better \| \| `non_live_multiple_ast` \| 90 \| percent \| reported_task_score \| Higher is better \| \| `non_live_parallel_ast` \| 93.5 \| percent \| reported_task_score \| Higher is better \| \| `non_live_parallel_multiple_ast` \| 92 \| percent \| reported_task_score \| Higher is better \| \| `live_acc` \| 65.8 \| percent \| reported_task_score \| Higher is better \| \| `live_simple_ast` \| 73.26 \| percent \| reported_task_score \| Higher is better \| \| `live_multiple_ast` \| 63.82 \| percent \| reported_task_score \| Higher is better \| \| `live_parallel_ast` \| 75 \| percent \| reported_task_score \| Higher is better \| \| `live_parallel_multiple_ast` \| 66.67 \| percent \| reported_task_score \| Higher is better \| \| `multi_turn_acc` \| 13.5 \| percent \| reported_task_score \| Higher is better \| \| `multi_turn_base` \| 20 \| percent \| reported_task_score \| Higher is better \| \| `multi_turn_miss_func` \| 1.5 \| percent \| reported_task_score \| Higher is better \| \| `multi_turn_miss_param` \| 15 \| percent \| reported_task_score \| Higher is better \| \| `multi_turn_long_context` \| 17.5 \| percent \| reported_task_score \| Higher is better \| \| `web_search_acc` \| 21 \| percent \| reported_task_score \| Higher is better \| \| `web_search_base` \| 26 \| percent \| reported_task_score \| Higher is better \| \| `web_search_no_snippet` \| 16 \| percent \| reported_task_score \| Higher is better \| \| `memory_acc` \| 20.65 \| percent \| reported_task_score \| Higher is better \| \| `memory_kv` \| 3.87 \| percent \| reported_task_score \| Higher is better \| \| `memory_vector` \| 6.45 \| percent \| reported_task_score \| Higher is better \| \| `memory_recursive_summarization` \| 51.61 \| percent \| reported_task_score \| Higher is better \| \| `relevance_detection` \| 43.75 \| percent \| reported_task_score \| Higher is better \| \| `irrelevance_detection` \| 92.5 \| percent \| reported_task_score \| Higher is better \| \| `latency_p95` \| 1.67 \| seconds \| per_call_p95 \| Lower is better \| ### Configuration mode FC sourceRelease 2025-12-16 ### Reported statistics rank 52 ### Source [Original source](https://api.github.com/repos/HuanzhiMao/BFCL-Result/contents/2025-12-16/score/data_overall.csv?ref=cadd76a8dc62984e7bf15ecaf358f070bae745cc) Source Berkeley Function Calling Leaderboard Original model label Gemini-2.5-Flash-Lite Observed 2026-10-22T02:40:09.731Z Evidence SHA-256 `ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6` Source locator `/rows/52` |  |  |  |  |  |  |  |
| [Berkeley Function Calling Leaderboard](https://benchize.com/benchmarks/bfcl%3Aoverall.md) | 28.03% | — | 22 / 26 | $7.05 | 1s | [Berkeley Function Calling Leaderboard](https://api.github.com/repos/HuanzhiMao/BFCL-Result/contents/2025-12-16/score/data_overall.csv?ref=cadd76a8dc62984e7bf15ecaf358f070bae745cc) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 28.03 \| percent \| reported \| Higher is better \| \| `cost_total` \| 7.05 \| USD \| evaluation_total \| Lower is better \| \| `latency_mean` \| 1 \| seconds \| per_call_mean \| Lower is better \| \| `latency_sd` \| 4.75 \| seconds \| per_call_sd \| Lower is better \| \| `non_live_ast_acc` \| 83.9 \| percent \| reported_task_score \| Higher is better \| \| `non_live_simple_ast` \| 70.08 \| percent \| reported_task_score \| Higher is better \| \| `non_live_multiple_ast` \| 86 \| percent \| reported_task_score \| Higher is better \| \| `non_live_parallel_ast` \| 90 \| percent \| reported_task_score \| Higher is better \| \| `non_live_parallel_multiple_ast` \| 89.5 \| percent \| reported_task_score \| Higher is better \| \| `live_acc` \| 54.85 \| percent \| reported_task_score \| Higher is better \| \| `live_simple_ast` \| 67.05 \| percent \| reported_task_score \| Higher is better \| \| `live_multiple_ast` \| 51.66 \| percent \| reported_task_score \| Higher is better \| \| `live_parallel_ast` \| 75 \| percent \| reported_task_score \| Higher is better \| \| `live_parallel_multiple_ast` \| 50 \| percent \| reported_task_score \| Higher is better \| \| `multi_turn_acc` \| 7.63 \| percent \| reported_task_score \| Higher is better \| \| `multi_turn_base` \| 10 \| percent \| reported_task_score \| Higher is better \| \| `multi_turn_miss_func` \| 5 \| percent \| reported_task_score \| Higher is better \| \| `multi_turn_miss_param` \| 6.5 \| percent \| reported_task_score \| Higher is better \| \| `multi_turn_long_context` \| 9 \| percent \| reported_task_score \| Higher is better \| \| `web_search_acc` \| 0 \| percent \| reported_task_score \| Higher is better \| \| `web_search_base` \| 0 \| percent \| reported_task_score \| Higher is better \| \| `web_search_no_snippet` \| 0 \| percent \| reported_task_score \| Higher is better \| \| `memory_acc` \| 12.69 \| percent \| reported_task_score \| Higher is better \| \| `memory_kv` \| 1.94 \| percent \| reported_task_score \| Higher is better \| \| `memory_vector` \| 6.45 \| percent \| reported_task_score \| Higher is better \| \| `memory_recursive_summarization` \| 29.68 \| percent \| reported_task_score \| Higher is better \| \| `relevance_detection` \| 50 \| percent \| reported_task_score \| Higher is better \| \| `irrelevance_detection` \| 93.33 \| percent \| reported_task_score \| Higher is better \| \| `latency_p95` \| 1.4 \| seconds \| per_call_p95 \| Lower is better \| ### Configuration mode Prompt sourceRelease 2025-12-16 ### Reported statistics rank 73 ### Source [Original source](https://api.github.com/repos/HuanzhiMao/BFCL-Result/contents/2025-12-16/score/data_overall.csv?ref=cadd76a8dc62984e7bf15ecaf358f070bae745cc) Source Berkeley Function Calling Leaderboard Original model label Gemini-2.5-Flash-Lite Observed 2026-10-22T02:40:09.731Z Evidence SHA-256 `ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6` Source locator `/rows/73` |  |  |  |  |  |  |  |
| [SVGBench Arena](https://benchize.com/benchmarks/svgbench%3Aarena.md) | 1,453 | — | 87 / 191 | — | — | [svgbench](https://svgbench.ai/api/leaderboard?shape=2) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1453 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_google_gemini_2_5_flash_lite ### Reported statistics coverageCount 27 draws 4 judged 79 losses 35 rank 118 ratingDeviation 28 wins 40 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Gemini 2.5 Flash Lite Observed 2026-10-22T04:30:04.538Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/114` |  |  |  |  |  |  |  |
| [SAGE / overall](https://benchize.com/benchmarks/vals-ai%3Asage%3Aoverall.md) | 27.53% | SE ±3.12 pp | 40 / 41 | $0.000929 | 13.78source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 27.533 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.000929 \| USD \| per_test \| Lower is better \| \| `latency` \| 13.781 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Google reasoning Not reported Reasoning effort unknown Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.12 pp sourcePopulation 91 stderr 3.124 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label google/gemini-2.5-flash-lite Source version 1 Observed 2026-10-22T02:10:22.165Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/overall/google~1gemini-2.5-flash-lite` |  |  |  |  |  |  |  |
| [Judgemark v2.1](https://benchize.com/benchmarks/eq-bench%3Ajudgemark-v2.md) | 55.99% | — | 34 / 39 | — | — | [eq bench · judgemark-v2](https://eqbench.com/judgemark-v2.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `judgemark_score` \| 55.99 \| percent \| overall \| Higher is better \| \| `stability` \| 0.483 \| score_fraction \| overall \| Higher is better \| \| `separability` \| 0.607 \| score_fraction \| overall \| Higher is better \| \| `human_corr` \| 0.448 \| correlation \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol judgemark-v2 sourceModelVersion gemini-2.5-flash-lite ### Source [Original source](https://eqbench.com/judgemark-v2.js) Source eq bench Original model label gemini-2.5-flash-lite Source version judgemark-v2 Observed 2026-10-21T16:35:03.564Z Evidence SHA-256 `070cc3fbd6f0333dde2b52bec4329ea3fba7eccbf016bbbbef95e0f8b2197781` Source locator `/leaderboardDataV2/16` |  |  |  |  |  |  |  |

---
Cite as: Gemini 2.5 Flash Lite — Benchize, https://benchize.com/models/gemini-2-5-flash-lite (retrieved 2026-10-22)