# Step 3.7 Flash

> Source: Benchize (https://benchize.com) — https://benchize.com/models/step-3-7-flash. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/step-3-7-flash.

StepFun

Canonical URL: https://benchize.com/models/step-3-7-flash
Last updated: Thu, 22 Oct 2026 05:30:58 GMT

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

StepFun

## Benchmarks

| Benchmark | Score | ± | Rank | Cost | Source |  |
| --- | --- | --- | --- | --- | --- | --- |
| [DesignArena Overall frontend coding](https://benchize.com/benchmarks/designarena%3Acode.md) | 1,182elo | SE ±2.2 | 52 / 116 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=code) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1182 \| elo \| code \| Higher is better \| ### Configuration arenaType models category allcategories inputModality text sourceModelVersion step-3.7-flash variationName public ### Reported statistics Uncertainty Standard error: ±2.2 averageGenerationTimeMs 117732 battles 30035 losses 17330 standardError 2.2009 winRate 42.3 wins 12705 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=code) Source designarena Original model label Step 3.7 Flash Source version public Observed 2026-10-21T16:37:57.301Z Evidence SHA-256 `0c897b58670f5e352bd123db999a40c0d1781a443964c502b90774a76a3a7758` Source locator `/data/84` |  |  |  |  |  |  |
| [ArXivMath 06/2026](https://benchize.com/benchmarks/matharena%3Aarxiv--june.md) | 30.56% | 95% CI 23.04–38.08% | 27 / 27 | 0.05usd per problem | [matharena · arxiv--june](https://matharena.ai/competition_tables/arxiv--june) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 30.56 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.045 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv--june predicted false sourceModelName Step 3.7 Flash sourceModelVersion stepfun/3.7-flash ### Reported statistics Uncertainty 95% confidence interval: 23.04–38.08% confidenceInterval95 7.52 problems 48 ### Source [Original source](https://matharena.ai/competition_tables/arxiv--june) Source matharena Original model label Step 3.7 Flash Source version arxiv--june Observed 2026-10-22T05:30:09.097Z Evidence SHA-256 `6832faff9be7e16a6c646c59017e30a2caedebe8cf02caf617a5ed9d8fb03bab` Source locator `/table/rows/28` |  |  |  |  |  |  |
| [BrokenArXiv 04/2026](https://benchize.com/benchmarks/matharena%3Aarxiv_false--april.md) | 18.85% | 95% CI 11.91–25.79% | 13 / 18 | 0.03usd per problem | [matharena · arxiv_false--april](https://matharena.ai/competition_tables/arxiv_false--april) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 18.85 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.027 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv_false--april predicted false sourceModelName Step 3.7 Flash sourceModelVersion stepfun/3.7-flash ### Reported statistics Uncertainty 95% confidence interval: 11.91–25.79% confidenceInterval95 6.94 problems 61 ### Source [Original source](https://matharena.ai/competition_tables/arxiv_false--april) Source matharena Original model label Step 3.7 Flash Source version arxiv_false--april Observed 2026-10-22T05:30:06.112Z Evidence SHA-256 `e543f14dac0ba9663e8104a87738726c9848b89171a53fdca89b7baa4a892399` Source locator `/table/rows/13` |  |  |  |  |  |  |
| [DesignArena Browser game generation](https://benchize.com/benchmarks/designarena%3Agame-dev.md) | 1,158elo | — | 66 / 117 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=game-dev) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1158 \| elo \| game-dev \| Higher is better \| ### Configuration arenaType models category gamedev inputModality Not reported sourceModelVersion step-3.7-flash variationName public ### Reported statistics averageGenerationTimeMs 148342 battles 4550 losses 2801 standardError Not reported winRate 38.4 wins 1749 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=game-dev) Source designarena Original model label Step 3.7 Flash Source version public Observed 2026-10-21T16:38:01.100Z Evidence SHA-256 `53db6a89112ce8cdf644568c666d4b8309aece764cfcedb291ffd52ae3934e30` Source locator `/data/99` |  |  |  |  |  |  |
| [ArXivMath 03/2026](https://benchize.com/benchmarks/matharena%3Aarxiv--march.md) | 45% | 95% CI 36.1–53.9% | 13 / 14 | 0.04usd per problem | [matharena · arxiv--march](https://matharena.ai/competition_tables/arxiv--march) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 45.00 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.043 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv--march predicted false sourceModelName Step 3.7 Flash sourceModelVersion stepfun/3.7-flash ### Reported statistics Uncertainty 95% confidence interval: 36.1–53.9% confidenceInterval95 8.90 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/arxiv--march) Source matharena Original model label Step 3.7 Flash Source version arxiv--march Observed 2026-10-22T05:30:08.323Z Evidence SHA-256 `9cb6d9cc26949fcb2b6affed792584b4bfe9d6168e1fc5cf2c13b38d3479715b` Source locator `/table/rows/13` |  |  |  |  |  |  |
| [Judgemark v4](https://benchize.com/benchmarks/eq-bench%3Ajudgemark-v4.md) | 28.05% | CI 26.23–36.51% | 35 / 38 | — | [eq bench · judgemark-v4](https://eqbench.com/judgemark-v4.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.280475 \| score_fraction \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol judgemark-v4 sourceModelVersion stepfun-ai/Step-3.7-Flash ### Reported statistics Uncertainty Confidence interval: 26.23–36.51% confidenceIntervalHigh 0.365120 confidenceIntervalLow 0.262261 ### Source [Original source](https://eqbench.com/judgemark-v4.js) Source eq bench Original model label stepfun-ai/Step-3.7-Flash Source version judgemark-v4 Observed 2026-10-22T05:10:06.884Z Evidence SHA-256 `2b0d42aef4f614dd199dc38399be7b88075a919db52020c3759f190defc92a4d` Source locator `/leaderboardDataJudgemarkV4/37` |  |  |  |  |  |  |
| [DesignArena 3D design generation](https://benchize.com/benchmarks/designarena%3A3d-design.md) | 1,129elo | — | 59 / 110 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=3d-design) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1129 \| elo \| 3d-design \| Higher is better \| ### Configuration arenaType models category 3d inputModality Not reported sourceModelVersion step-3.7-flash variationName public ### Reported statistics averageGenerationTimeMs 103836 battles 6906 losses 4115 standardError Not reported winRate 40.4 wins 2791 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=3d-design) Source designarena Original model label Step 3.7 Flash Source version public Observed 2026-10-21T16:37:58.515Z Evidence SHA-256 `bcc0267f7bc7e9ec112306b3a35413cf78bbccbfaa838356232d5d5ed0b83d0f` Source locator `/data/93` |  |  |  |  |  |  |
| [Apex](https://benchize.com/benchmarks/matharena%3Aapex--apex_2025.md) | 14.58% | 95% CI 7.52–21.64% | 14 / 31 | 0.08usd per problem | [matharena · apex--apex_2025](https://matharena.ai/competition_tables/apex--apex_2025) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 14.58 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.075 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition apex--apex_2025 predicted false sourceModelName Step 3.7 Flash sourceModelVersion stepfun/3.7-flash ### Reported statistics Uncertainty 95% confidence interval: 7.52–21.64% confidenceInterval95 7.06 problems 12 ### Source [Original source](https://matharena.ai/competition_tables/apex--apex_2025) Source matharena Original model label Step 3.7 Flash Source version apex--apex_2025 Observed 2026-10-22T05:30:13.849Z Evidence SHA-256 `20b28370d9d7f5a15a19fc9e4226c9857cdb07bc42b32ccec508e687b7b9f3fc` Source locator `/table/rows/16` |  |  |  |  |  |  |
| [DesignArena ASCII art generation](https://benchize.com/benchmarks/designarena%3Aascii.md) | 1,152elo | — | 36 / 65 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=ascii) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1152 \| elo \| ascii \| Higher is better \| ### Configuration arenaType models category ascii inputModality Not reported sourceModelVersion step-3.7-flash variationName public ### Reported statistics averageGenerationTimeMs 109891 battles 609 losses 335 standardError Not reported winRate 45 wins 274 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ascii) Source designarena Original model label Step 3.7 Flash Source version public Observed 2026-10-21T16:38:03.513Z Evidence SHA-256 `0603b8c65b44ee887f5b566feb469465f59635137a6ac5c6d94c23bcf3776311` Source locator `/data/52` |  |  |  |  |  |  |
| [DesignArena Website generation](https://benchize.com/benchmarks/designarena%3Awebsite.md) | 1,196elo | — | 53 / 123 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=website) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1196 \| elo \| website \| Higher is better \| ### Configuration arenaType models category website inputModality text sourceModelVersion step-3.7-flash variationName public ### Reported statistics averageGenerationTimeMs 119047 battles 18427 losses 10333 standardError Not reported winRate 43.9 wins 8094 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=website) Source designarena Original model label Step 3.7 Flash Source version public Observed 2026-10-21T16:37:57.757Z Evidence SHA-256 `51873e97776a3c5ae706b24cc2c60384793dd18398df970e213a8e7c276d8ac0` Source locator `/data/86` |  |  |  |  |  |  |
| [ArXivMath 05/2026](https://benchize.com/benchmarks/matharena%3Aarxiv--may.md) | 46.67% | 95% CI 37.74–55.6% | 22 / 23 | 0.05usd per problem | [matharena · arxiv--may](https://matharena.ai/competition_tables/arxiv--may) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 46.67 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.054 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv--may predicted false sourceModelName Step 3.7 Flash sourceModelVersion stepfun/3.7-flash ### Reported statistics Uncertainty 95% confidence interval: 37.74–55.6% confidenceInterval95 8.93 problems 40 ### Source [Original source](https://matharena.ai/competition_tables/arxiv--may) Source matharena Original model label Step 3.7 Flash Source version arxiv--may Observed 2026-10-22T05:30:08.858Z Evidence SHA-256 `758e1bba77e36f4ced2a51b4bc0d46bd956ed94ef6f57e93e1a974b75e76a4ce` Source locator `/table/rows/22` |  |  |  |  |  |  |
| [DesignArena SVG generation](https://benchize.com/benchmarks/designarena%3Asvgs.md) | 1,085elo | — | 60 / 77 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=svgs) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1085 \| elo \| svgs \| Higher is better \| ### Configuration arenaType models category svg inputModality Not reported sourceModelVersion step-3.7-flash variationName public ### Reported statistics averageGenerationTimeMs 63348 battles 2185 losses 1368 standardError Not reported winRate 37.4 wins 817 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=svgs) Source designarena Original model label Step 3.7 Flash Source version public Observed 2026-10-21T16:38:03.249Z Evidence SHA-256 `8cbc34a474a66ef5c64f3ffe557df9b55bf7e13368c07c0214223e3ed8f3f21e` Source locator `/data/94` |  |  |  |  |  |  |
| [DesignArena Data visualization generation](https://benchize.com/benchmarks/designarena%3Adata-viz.md) | 1,172elo | — | 62 / 99 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=data-viz) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1172 \| elo \| data-viz \| Higher is better \| ### Configuration arenaType models category dataviz inputModality Not reported sourceModelVersion step-3.7-flash variationName public ### Reported statistics averageGenerationTimeMs 88961 battles 1716 losses 980 standardError Not reported winRate 42.9 wins 736 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=data-viz) Source designarena Original model label Step 3.7 Flash Source version public Observed 2026-10-21T16:37:58.264Z Evidence SHA-256 `a895f6f1a25fa8eb01f821c2097ddec4f884de7bd22f1b8a22e82e6679b71849` Source locator `/data/91` |  |  |  |  |  |  |
| [BrokenArXiv 06/2026](https://benchize.com/benchmarks/matharena%3Aarxiv_false--june.md) | 15.74% | 95% CI 10.13–21.35% | 22 / 26 | 0.03usd per problem | [matharena · arxiv_false--june](https://matharena.ai/competition_tables/arxiv_false--june) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 15.74 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.027 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv_false--june predicted false sourceModelName Step 3.7 Flash sourceModelVersion stepfun/3.7-flash ### Reported statistics Uncertainty 95% confidence interval: 10.13–21.35% confidenceInterval95 5.61 problems 54 ### Source [Original source](https://matharena.ai/competition_tables/arxiv_false--june) Source matharena Original model label Step 3.7 Flash Source version arxiv_false--june Observed 2026-10-22T05:30:06.636Z Evidence SHA-256 `f6d7e2280d05706643d46ae7786bd3fad6d912e4893781c3f62c73deebf38459` Source locator `/table/rows/23` |  |  |  |  |  |  |
| [BrokenArXiv 05/2026](https://benchize.com/benchmarks/matharena%3Aarxiv_false--may.md) | 8.5% | 95% CI 3.03–13.97% | 20 / 22 | 0.03usd per problem | [matharena · arxiv_false--may](https://matharena.ai/competition_tables/arxiv_false--may) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 8.50 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.027 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv_false--may predicted false sourceModelName Step 3.7 Flash sourceModelVersion stepfun/3.7-flash ### Reported statistics Uncertainty 95% confidence interval: 3.03–13.97% confidenceInterval95 5.47 problems 50 ### Source [Original source](https://matharena.ai/competition_tables/arxiv_false--may) Source matharena Original model label Step 3.7 Flash Source version arxiv_false--may Observed 2026-10-22T05:30:06.354Z Evidence SHA-256 `b317fca30109e8c78ed5d2b835fe227b8cfbee3b6f9cb6d7aaeadca866660969` Source locator `/table/rows/20` |  |  |  |  |  |  |
| [ArXivMath 02/2026](https://benchize.com/benchmarks/matharena%3Aarxiv--february.md) | 32.03% | 95% CI 23.95–40.11% | 17 / 20 | 0.06usd per problem | [matharena · arxiv--february](https://matharena.ai/competition_tables/arxiv--february) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 32.03 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.055 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv--february predicted false sourceModelName Step 3.7 Flash sourceModelVersion stepfun/3.7-flash ### Reported statistics Uncertainty 95% confidence interval: 23.95–40.11% confidenceInterval95 8.08 problems 32 ### Source [Original source](https://matharena.ai/competition_tables/arxiv--february) Source matharena Original model label Step 3.7 Flash Source version arxiv--february Observed 2026-10-22T05:30:08.096Z Evidence SHA-256 `3bc5b0a1eb91a0bdaa3d0942ebf82327a8664334b225ae3b2dc1d8b4f57efa51` Source locator `/table/rows/18` |  |  |  |  |  |  |
| [BrokenArXiv 03/2026](https://benchize.com/benchmarks/matharena%3Aarxiv_false--march.md) | 10.71% | 95% CI 4.98–16.44% | 10 / 14 | 0.02usd per problem | [matharena · arxiv_false--march](https://matharena.ai/competition_tables/arxiv_false--march) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 10.71 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.023 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv_false--march predicted false sourceModelName Step 3.7 Flash sourceModelVersion stepfun/3.7-flash ### Reported statistics Uncertainty 95% confidence interval: 4.98–16.44% confidenceInterval95 5.73 problems 56 ### Source [Original source](https://matharena.ai/competition_tables/arxiv_false--march) Source matharena Original model label Step 3.7 Flash Source version arxiv_false--march Observed 2026-10-22T05:30:05.839Z Evidence SHA-256 `b2ea8c773acad8b54736938938d6ee37fa533bfc5b985eefc303733bfcb0c6f0` Source locator `/table/rows/10` |  |  |  |  |  |  |
| [ArXivLean 06/2026](https://benchize.com/benchmarks/matharena%3Aarxivlean--june.md) | 0% | 95% CI 0–0% | 11 / 11 | 0.53usd per problem | [matharena · arxivlean--june](https://matharena.ai/competition_tables/arxivlean--june) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0.00 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.53 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxivlean--june predicted false sourceModelName Step 3.7 Flash sourceModelVersion stepfun/3.7-flash ### Reported statistics Uncertainty 95% confidence interval: 0–0% confidenceInterval95 0.00 problems 46 ### Source [Original source](https://matharena.ai/competition_tables/arxivlean--june) Source matharena Original model label Step 3.7 Flash Source version arxivlean--june Observed 2026-10-22T05:30:04.813Z Evidence SHA-256 `0869c2556b20f1879eb0ea99ea8151e805471cd9d6be57c652f764a775491b7d` Source locator `/table/rows/13` |  |  |  |  |  |  |
| [ArXivMath Overall](https://benchize.com/benchmarks/matharena%3Aoverall--final_answer_comps.md) | 68.51% | 95% CI 65.31–71.71% | 12 / 20 | 0.04usd 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` \| 68.51 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.042 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition overall--final_answer_comps predicted false sourceModelName Step 3.7 Flash sourceModelVersion stepfun/3.7-flash ### Reported statistics Uncertainty 95% confidence interval: 65.31–71.71% confidenceInterval95 3.20 problems Not reported ### Source [Original source](https://matharena.ai/competition_tables/overall--final_answer_comps) Source matharena Original model label Step 3.7 Flash Source version overall--final_answer_comps Observed 2026-10-22T05:30:11.571Z Evidence SHA-256 `8b08b20c1ac5aec9a829d234469bc39d40b0eb189790d84b7264c2756ffa161e` Source locator `/table/rows/13` |  |  |  |  |  |  |
| [BrokenArXiv 02/2026](https://benchize.com/benchmarks/matharena%3Aarxiv_false--february.md) | 12.1% | 95% CI 3.98–20.22% | 8 / 15 | 0.02usd per problem | [matharena · arxiv_false--february](https://matharena.ai/competition_tables/arxiv_false--february) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 12.10 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.023 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv_false--february predicted false sourceModelName Step 3.7 Flash sourceModelVersion stepfun/3.7-flash ### Reported statistics Uncertainty 95% confidence interval: 3.98–20.22% confidenceInterval95 8.12 problems 31 ### Source [Original source](https://matharena.ai/competition_tables/arxiv_false--february) Source matharena Original model label Step 3.7 Flash Source version arxiv_false--february Observed 2026-10-22T05:30:05.567Z Evidence SHA-256 `a6bc6fc18da7dd181ed727da924f9569d3e323c31c1aba9a4d9fa3bff492bee3` Source locator `/table/rows/7` |  |  |  |  |  |  |
| [OpenVibeEval Accessibility](https://benchize.com/benchmarks/openvibeeval%3Aaccessibility.md) | 66 | — | 21 / 26 | — | [openvibeeval](https://openvibeeval.com/leaderboard/) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `adjusted_score` \| 66 \| score \| sample_size_adjusted_accessibility \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Step 3.7 Flash thinkingEnabled Not reported ### Reported statistics runCount 8 ### Source [Original source](https://openvibeeval.com/leaderboard/) Source openvibeeval Original model label Step 3.7 Flash Evaluated 2026-08-05 Observed 2026-10-21T16:32:04.885Z Evidence SHA-256 `9b2e7d6060910e3dc7083a6a7f67377601ce78806b2b6b7693cf8d047dd63fbb` Source locator `/rows/34` |  |  |  |  |  |  |
| [Apex Shortlist](https://benchize.com/benchmarks/matharena%3Aapex--shortlist_2025.md) | 76.6% | 95% CI 70.55–82.65% | 10 / 25 | 0.06usd per problem | [matharena · apex--shortlist_2025](https://matharena.ai/competition_tables/apex--shortlist_2025) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 76.60 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.062 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition apex--shortlist_2025 predicted false sourceModelName Step 3.7 Flash sourceModelVersion stepfun/3.7-flash ### Reported statistics Uncertainty 95% confidence interval: 70.55–82.65% confidenceInterval95 6.05 problems 47 ### Source [Original source](https://matharena.ai/competition_tables/apex--shortlist_2025) Source matharena Original model label Step 3.7 Flash Source version apex--shortlist_2025 Observed 2026-10-22T05:30:14.141Z Evidence SHA-256 `74513abecacb4d230d741f4d6df425ce878fb450220e88a1a6823524476c2989` Source locator `/table/rows/11` |  |  |  |  |  |  |
| [ArXivMath 04/2026](https://benchize.com/benchmarks/matharena%3Aarxiv--april.md) | 35.83% | 95% CI 27.25–44.41% | 19 / 20 | 0.04usd per problem | [matharena · arxiv--april](https://matharena.ai/competition_tables/arxiv--april) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 35.83 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.043 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv--april predicted false sourceModelName Step 3.7 Flash sourceModelVersion stepfun/3.7-flash ### Reported statistics Uncertainty 95% confidence interval: 27.25–44.41% confidenceInterval95 8.58 problems 40 ### Source [Original source](https://matharena.ai/competition_tables/arxiv--april) Source matharena Original model label Step 3.7 Flash Source version arxiv--april Observed 2026-10-22T05:30:08.600Z Evidence SHA-256 `5139c835884bfab38f18d23a248814af4680927310bc5cd2a86ea2eab779e0a7` Source locator `/table/rows/19` |  |  |  |  |  |  |
| [DesignArena Image to HTML](https://benchize.com/benchmarks/designarena%3Aimage-to-html.md) | 1,119elo | — | 34 / 35 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=image-to-html) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1119 \| elo \| image-to-html \| Higher is better \| ### Configuration arenaType models category website inputModality image sourceModelVersion step-3.7-flash variationName public ### Reported statistics averageGenerationTimeMs 118312 battles 2309 losses 1377 standardError Not reported winRate 40.4 wins 932 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=image-to-html) Source designarena Original model label Step 3.7 Flash Source version public Observed 2026-10-21T16:37:58.959Z Evidence SHA-256 `94f97ebbdd53a8c56f138b620e59b3a9b35c66c3954dcaaa1b2ed4c71518b404` Source locator `/data/42` |  |  |  |  |  |  |
| [DesignArena UI component generation](https://benchize.com/benchmarks/designarena%3Aui-components.md) | 1,179elo | — | 55 / 112 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=ui-components) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1179 \| elo \| ui-components \| Higher is better \| ### Configuration arenaType models category uicomponent inputModality Not reported sourceModelVersion step-3.7-flash variationName public ### Reported statistics averageGenerationTimeMs 102653 battles 2159 losses 1255 standardError Not reported winRate 41.9 wins 904 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ui-components) Source designarena Original model label Step 3.7 Flash Source version public Observed 2026-10-21T16:37:57.993Z Evidence SHA-256 `46482ec1b4012638eace65493daea4750e2088098018fd9d5fc46126fc1f8557` Source locator `/data/86` |  |  |  |  |  |  |
| [AIME 2026](https://benchize.com/benchmarks/aime-2026.md) | 95% | 95% CI 91.1–98.9% | 15 / 21 | 0.02usd per problem | [matharena · aime--aime_2026](https://matharena.ai/competition_tables/aime--aime_2026) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 95.00 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.015 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition aime--aime_2026 predicted false sourceModelName Step 3.7 Flash sourceModelVersion stepfun/3.7-flash ### Reported statistics Uncertainty 95% confidence interval: 91.1–98.9% confidenceInterval95 3.90 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/aime--aime_2026) Source matharena Original model label Step 3.7 Flash Source version aime--aime_2026 Observed 2026-10-22T05:30:13.366Z Evidence SHA-256 `58b3ac1e0805975eba566c493b8e0165d41eb7ca517218106e112529fb6342de` Source locator `/table/rows/17` |  |  |  |  |  |  |
| [HMMT Feb 2026](https://benchize.com/benchmarks/matharena%3Ahmmt--hmmt_feb_2026.md) | 87.88% | 95% CI 80.01–95.75% | 15 / 21 | 0.02usd 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` \| 87.88 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.024 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition hmmt--hmmt_feb_2026 predicted false sourceModelName Step 3.7 Flash sourceModelVersion stepfun/3.7-flash ### Reported statistics Uncertainty 95% confidence interval: 80.01–95.75% confidenceInterval95 7.87 problems 33 ### Source [Original source](https://matharena.ai/competition_tables/hmmt--hmmt_feb_2026) Source matharena Original model label Step 3.7 Flash Source version hmmt--hmmt_feb_2026 Observed 2026-10-22T05:30:13.595Z Evidence SHA-256 `0dce922c33a54d29d4a1872a42d74077b491915c80d8433f4b379ea0b78bb979` Source locator `/table/rows/16` |  |  |  |  |  |  |

---
Cite as: Step 3.7 Flash — Benchize, https://benchize.com/models/step-3-7-flash (retrieved 2026-10-22)