# Qwen3.5-9B > Source: Benchize (https://benchize.com) — https://benchize.com/models/qwen3-5-9b. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/qwen3-5-9b. Alibaba Canonical URL: https://benchize.com/models/qwen3-5-9b 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. Alibaba ## Benchmarks | Benchmark | Score | ± | Rank | Cost | Source | | | --- | --- | --- | --- | --- | --- | --- | | [Judgemark v4](https://benchize.com/benchmarks/eq-bench%3Ajudgemark-v4.md) | 32.44% | CI 28.84–41.55% | 32 / 38 | — | [eq bench · judgemark-v4](https://eqbench.com/judgemark-v4.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.324392 \| score_fraction \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol judgemark-v4 sourceModelVersion Qwen/Qwen3.5-9B ### Reported statistics Uncertainty Confidence interval: 28.84–41.55% confidenceIntervalHigh 0.415527 confidenceIntervalLow 0.288405 ### Source [Original source](https://eqbench.com/judgemark-v4.js) Source eq bench Original model label Qwen/Qwen3.5-9B Source version judgemark-v4 Observed 2026-10-21T16:35:03.901Z Evidence SHA-256 `2b0d42aef4f614dd199dc38399be7b88075a919db52020c3759f190defc92a4d` Source locator `/leaderboardDataJudgemarkV4/34` | | | | | | | | [ArXivMath 01/2026](https://benchize.com/benchmarks/matharena%3Aarxiv--january.md) | 44.57% | 95% CI 34.41–54.73% | 18 / 18 | 0.008usd per problem | [matharena · arxiv--january](https://matharena.ai/competition_tables/arxiv--january) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 44.57 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.008 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv--january predicted false sourceModelName Qwen3.5-9B sourceModelVersion qwen/qwen3.5_9b ### Reported statistics Uncertainty 95% confidence interval: 34.41–54.73% confidenceInterval95 10.16 problems 23 ### Source [Original source](https://matharena.ai/competition_tables/arxiv--january) Source matharena Original model label Qwen3.5-9B Source version arxiv--january Observed 2026-10-21T16:52:27.447Z Evidence SHA-256 `e895f6ccd0711bb1a512b580bab39de8f977c57f83bf492527e4fc710315d706` Source locator `/table/rows/23` | | | | | | | | [GPQA Diamond](https://benchize.com/benchmarks/gpqa-diamond.md) | 78.98% | SE ±2.37 pp | 74 / 126 | — | [epoch ai · GPQA diamond](https://epoch.ai/data/benchmark_data.zip#file=gpqa_diamond.csv) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.7897727272727273 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.7897727272727273 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion GPQA diamond reasoningBudget Not reported Reasoning effort Not reported sourceModelVersion qwen3.5-9B ### Reported statistics Uncertainty Standard error: ±2.37 pp standardError 0.02365568030958479 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=gpqa_diamond.csv) Source epoch ai Original model label qwen3.5-9B Source version GPQA diamond Evaluated 2026-08-27T14:30:17.000Z Observed 2026-10-22T03:00:05.281Z Evidence SHA-256 `9ef0b938bdd8406b029d595983ee8ad3a80bd9d64b82605b91b5ce39ba650c39` Source locator `/rows/51` | | | | | | | | [OTIS Mock AIME 2024–2025](https://benchize.com/benchmarks/epoch-ai%3Aotis_mock_aime_2024_2025.md) | 42.78% | SE ±6.53 pp | 96 / 124 | — | [epoch ai · OTIS Mock AIME 2024-2025](https://epoch.ai/data/benchmark_data.zip#file=otis_mock_aime_2024_2025.csv) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.42777777777777776 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.42777777777777776 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion OTIS Mock AIME 2024-2025 reasoningBudget Not reported Reasoning effort Not reported sourceModelVersion qwen3.5-9B ### Reported statistics Uncertainty Standard error: ±6.53 pp standardError 0.06533819469304575 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=otis_mock_aime_2024_2025.csv) Source epoch ai Original model label qwen3.5-9B Source version OTIS Mock AIME 2024-2025 Evaluated 2026-08-27T14:30:39.000Z Observed 2026-10-22T03:00:05.281Z Evidence SHA-256 `b7c9da8c0587c82f1e0d814ceb496c24308380b997a16203b6e5d39eb07f4f50` Source locator `/rows/58` | | | | | | | | [SVGBench Arena](https://benchize.com/benchmarks/svgbench%3Aarena.md) | 1,473 | — | 78 / 191 | — | [svgbench](https://svgbench.ai/api/leaderboard?shape=2) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1473 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_qwen_qwen3_5_9b ### Reported statistics coverageCount 27 draws 3 judged 84 losses 36 rank 106 ratingDeviation 28 wins 45 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Qwen3.5-9B Observed 2026-10-22T04:30:04.538Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/102` | | | | | | | | [Judgemark v2.1](https://benchize.com/benchmarks/eq-bench%3Ajudgemark-v2.md) | 74.99% | — | 20 / 39 | — | [eq bench · judgemark-v2](https://eqbench.com/judgemark-v2.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `judgemark_score` \| 74.99 \| percent \| overall \| Higher is better \| \| `stability` \| 0.679 \| score_fraction \| overall \| Higher is better \| \| `separability` \| 0.779 \| score_fraction \| overall \| Higher is better \| \| `human_corr` \| 0.704 \| correlation \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol judgemark-v2 sourceModelVersion Qwen/Qwen3.5-9B ### Source [Original source](https://eqbench.com/judgemark-v2.js) Source eq bench Original model label Qwen/Qwen3.5-9B Source version judgemark-v2 Observed 2026-10-21T16:35:03.564Z Evidence SHA-256 `070cc3fbd6f0333dde2b52bec4329ea3fba7eccbf016bbbbef95e0f8b2197781` Source locator `/leaderboardDataV2/43` | | | | | | | | [ToneBench Scriptwriting](https://benchize.com/benchmarks/tonebench%3Ascripts.md) | 219.1 | Range 142.7–283.2 | 122 / 126 | — | [tonebench](https://benchmark.towardsai.com/data/leaderboard.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 219.1 \| rating \| reported \| Higher is better \| \| `overall` \| 50.16 \| percent \| reported \| Higher is better \| \| `anti_slop_numbers` \| 47.8 \| source_score \| rubric \| Higher is better \| \| `continuity_emotion` \| 47.41 \| source_score \| rubric \| Higher is better \| \| `cue_quality` \| 36.66 \| source_score \| rubric \| Higher is better \| \| `hook_strength` \| 62.85 \| source_score \| rubric \| Higher is better \| \| `length_adherence` \| 56.81 \| source_score \| rubric \| Higher is better \| \| `slop` \| 68.96 \| source_score \| rubric \| Higher is better \| \| `slop_score` \| 90.12 \| source_score \| rubric \| Higher is better \| \| `substance_accuracy` \| 51.13 \| source_score \| rubric \| Higher is better \| \| `tone_voice` \| 46.46 \| source_score \| rubric \| Higher is better \| \| `writing_quality` \| 42.47 \| source_score \| rubric \| Higher is better \| \| `youtube_best_practices` \| 47.97 \| source_score \| rubric \| Higher is better \| ### Configuration provider openrouter Reasoning effort unknown scoreScope 10_task_current sourceConfiguration qwen3-5-9b-or ### Reported statistics Uncertainty Reported interval: 142.7–283.2 interval [142.7,283.2] rank 129 runCount 5 ### Source [Original source](https://benchmark.towardsai.com/data/leaderboard.json) Source tonebench Original model label Qwen3.5 9B (thinking on) Evaluated 2026-10-08 Observed 2026-10-21T16:32:48.862Z Evidence SHA-256 `4264338337f418d3ded7ace250cad64fe12cacbd4b79a312bfaf0ae9268a01c3` Source locator `/rows/128` | | | | | | | | [ArXivMath Overall](https://benchize.com/benchmarks/matharena%3Aoverall--final_answer_comps.md) | 48.51% | 95% CI 45.71–51.31% | 20 / 20 | 0.007usd per problem | [matharena · overall--final_answer_comps](https://matharena.ai/competition_tables/overall--final_answer_comps) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 48.51 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.007 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition overall--final_answer_comps predicted false sourceModelName Qwen3.5-9B sourceModelVersion qwen/qwen3.5_9b ### Reported statistics Uncertainty 95% confidence interval: 45.71–51.31% confidenceInterval95 2.80 problems Not reported ### Source [Original source](https://matharena.ai/competition_tables/overall--final_answer_comps) Source matharena Original model label Qwen3.5-9B Source version overall--final_answer_comps Observed 2026-10-21T16:52:34.395Z Evidence SHA-256 `8b08b20c1ac5aec9a829d234469bc39d40b0eb189790d84b7264c2756ffa161e` Source locator `/table/rows/26` | | | | | | | | [AIME 2026](https://benchize.com/benchmarks/aime-2026.md) | 92.5% | 95% CI 87.79–97.21% | 19 / 21 | 0.005usd per problem | [matharena · aime--aime_2026](https://matharena.ai/competition_tables/aime--aime_2026) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 92.50 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.005 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition aime--aime_2026 predicted false sourceModelName Qwen3.5-9B sourceModelVersion qwen/qwen3.5_9b ### Reported statistics Uncertainty 95% confidence interval: 87.79–97.21% confidenceInterval95 4.71 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/aime--aime_2026) Source matharena Original model label Qwen3.5-9B Source version aime--aime_2026 Observed 2026-10-21T16:52:37.816Z Evidence SHA-256 `58b3ac1e0805975eba566c493b8e0165d41eb7ca517218106e112529fb6342de` Source locator `/table/rows/23` | | | | | | | | [HMMT Feb 2026](https://benchize.com/benchmarks/matharena%3Ahmmt--hmmt_feb_2026.md) | 71.21% | 95% CI 63.49–78.93% | 21 / 21 | 0.006usd per problem | [matharena · hmmt--hmmt_feb_2026](https://matharena.ai/competition_tables/hmmt--hmmt_feb_2026) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 71.21 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.006 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition hmmt--hmmt_feb_2026 predicted false sourceModelName Qwen3.5-9B sourceModelVersion qwen/qwen3.5_9b ### Reported statistics Uncertainty 95% confidence interval: 63.49–78.93% confidenceInterval95 7.72 problems 33 ### Source [Original source](https://matharena.ai/competition_tables/hmmt--hmmt_feb_2026) Source matharena Original model label Qwen3.5-9B Source version hmmt--hmmt_feb_2026 Observed 2026-10-21T16:52:38.351Z Evidence SHA-256 `0dce922c33a54d29d4a1872a42d74077b491915c80d8433f4b379ea0b78bb979` Source locator `/table/rows/29` | | | | | | | | [ArXivMath 02/2026](https://benchize.com/benchmarks/matharena%3Aarxiv--february.md) | 27.34% | 95% CI 19.62–35.06% | 20 / 20 | 0.008usd per problem | [matharena · arxiv--february](https://matharena.ai/competition_tables/arxiv--february) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 27.34 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.008 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv--february predicted false sourceModelName Qwen3.5-9B sourceModelVersion qwen/qwen3.5_9b ### Reported statistics Uncertainty 95% confidence interval: 19.62–35.06% confidenceInterval95 7.72 problems 32 ### Source [Original source](https://matharena.ai/competition_tables/arxiv--february) Source matharena Original model label Qwen3.5-9B Source version arxiv--february Observed 2026-10-21T16:52:27.963Z Evidence SHA-256 `3bc5b0a1eb91a0bdaa3d0942ebf82327a8664334b225ae3b2dc1d8b4f57efa51` Source locator `/table/rows/22` | | | | | | | | [Apex](https://benchize.com/benchmarks/matharena%3Aapex--apex_2025.md) | 0.52% | 95% CI -0.5–1.54% | 28 / 30 | 0.009usd per problem | [matharena · apex--apex_2025](https://matharena.ai/competition_tables/apex--apex_2025) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0.52 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.009 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition apex--apex_2025 predicted false sourceModelName Qwen3.5-9B sourceModelVersion qwen/qwen3.5_9b ### Reported statistics Uncertainty 95% confidence interval: -0.5–1.54% confidenceInterval95 1.02 problems 12 ### Source [Original source](https://matharena.ai/competition_tables/apex--apex_2025) Source matharena Original model label Qwen3.5-9B Source version apex--apex_2025 Observed 2026-10-21T16:52:38.728Z Evidence SHA-256 `20b28370d9d7f5a15a19fc9e4226c9857cdb07bc42b32ccec508e687b7b9f3fc` Source locator `/table/rows/41` | | | | | | | | [ArXivMath 12/2025](https://benchize.com/benchmarks/matharena%3Aarxiv--december.md) | 39.71% | 95% CI 28.08–51.34% | 8 / 12 | 0.008usd per problem | [matharena · arxiv--december](https://matharena.ai/competition_tables/arxiv--december) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 39.71 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.008 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv--december predicted false sourceModelName Qwen3.5-9B sourceModelVersion qwen/qwen3.5_9b ### Reported statistics Uncertainty 95% confidence interval: 28.08–51.34% confidenceInterval95 11.63 problems 17 ### Source [Original source](https://matharena.ai/competition_tables/arxiv--december) Source matharena Original model label Qwen3.5-9B Source version arxiv--december Observed 2026-10-21T16:52:26.934Z Evidence SHA-256 `6bbceef2706ad55e793e81bd959f7c1ec869f0ad04c6aa9013b2ad7b1a0820e3` Source locator `/table/rows/11` | | | | | | | | [Apex Shortlist](https://benchize.com/benchmarks/matharena%3Aapex--shortlist_2025.md) | 29.79% | 95% CI 23.25–36.33% | 24 / 24 | 0.009usd per problem | [matharena · apex--shortlist_2025](https://matharena.ai/competition_tables/apex--shortlist_2025) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 29.79 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.009 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition apex--shortlist_2025 predicted false sourceModelName Qwen3.5-9B sourceModelVersion qwen/qwen3.5_9b ### Reported statistics Uncertainty 95% confidence interval: 23.25–36.33% confidenceInterval95 6.54 problems 47 ### Source [Original source](https://matharena.ai/competition_tables/apex--shortlist_2025) Source matharena Original model label Qwen3.5-9B Source version apex--shortlist_2025 Observed 2026-10-21T16:52:39.300Z Evidence SHA-256 `74513abecacb4d230d741f4d6df425ce878fb450220e88a1a6823524476c2989` Source locator `/table/rows/35` | | | | | | | --- Cite as: Qwen3.5-9B — Benchize, https://benchize.com/models/qwen3-5-9b (retrieved 2026-10-22)