# Rapidata SVG generation — Preference

> Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/rapidata%3Asvg%3Arlb_1MFkkEMFnCNyKl. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/rapidata%3Asvg%3Arlb_1MFkkEMFnCNyKl.

Human pairwise evaluation of svg outputs, measuring preference. Scores are fitted using the Bradley–Terry preference model and expressed on the publisher’s Elo scale with 95% confidence intervals.

Canonical URL: https://benchize.com/benchmarks/rapidata%3Asvg%3Arlb_1MFkkEMFnCNyKl
Last updated: Wed, 21 Oct 2026 18:52:20 GMT

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

Human pairwise evaluation of svg outputs, measuring preference. Scores are fitted using the Bradley–Terry preference model and expressed on the publisher’s Elo scale with 95% confidence intervals.

Multimodal · Models tested: 37 · Score publishers: [rapidata](https://www.benchmark.ai/svg)

## Model results

| # | Model | Score | ± |  |
| --- | --- | --- | --- | --- |
| 1 | [Gemini 4 Argon](https://benchize.com/models/gemini-4-argon.md) | 1,753.02elo | CI 1,713.65–1,792.4 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1753.0223472511775 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1Xsgz12KP2Vun0 sourceModelVersion gemini-4-argon weighted false ### Reported statistics Uncertainty Confidence interval: 1,713.65–1,792.4 confidenceIntervalLowerOffset 39.37650392076739 confidenceIntervalUpperOffset 39.37650392076739 totalMatches 3295 wins 2793 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label gemini-4-argon Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/0` |  |  |  |  |
| 2 | [Claude Sonnet 5.5](https://benchize.com/models/claude-sonnet-5-5.md) | 1,598.61elo | CI 1,566.1–1,631.13 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1598.614322262301 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1WTTMAZoeeConj sourceModelVersion claude-sonnet-5.5 weighted false ### Reported statistics Uncertainty Confidence interval: 1,566.1–1,631.13 confidenceIntervalLowerOffset 32.51460617533621 confidenceIntervalUpperOffset 32.51460617533621 totalMatches 3601 wins 2861 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label claude-sonnet-5.5 Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/2` |  |  |  |  |
| 3 | [GPT-6.1 Sol](https://benchize.com/models/gpt-6-1-sol.md) | 1,577.42elo | CI 1,544.24–1,610.59 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1577.417524789626 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1WZA3S9cLmH0ve sourceModelVersion gpt-6.1-sol weighted false ### Reported statistics Uncertainty Confidence interval: 1,544.24–1,610.59 confidenceIntervalLowerOffset 33.17618357447009 confidenceIntervalUpperOffset 33.17618357447009 totalMatches 3548 wins 2789 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label gpt-6.1-sol Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/3` |  |  |  |  |
| 4 | [Muse Wonder](https://benchize.com/models/muse-wonder.md) | 1,550.32elo | CI 1,516.59–1,584.04 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1550.3153038483451 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1XneOLqGOEIX5L sourceModelVersion muse-wonder weighted false ### Reported statistics Uncertainty Confidence interval: 1,516.59–1,584.04 confidenceIntervalLowerOffset 33.724423040900774 confidenceIntervalUpperOffset 33.724423040900774 totalMatches 3343 wins 2589 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label muse-wonder Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/4` |  |  |  |  |
| 5 | [Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5.md) | 1,537.37elo | CI 1,506.07–1,568.67 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1537.3664192777635 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1VuObOzOuUSxTC sourceModelVersion claude-opus-5.5 weighted false ### Reported statistics Uncertainty Confidence interval: 1,506.07–1,568.67 confidenceIntervalLowerOffset 31.30030420331309 confidenceIntervalUpperOffset 31.30030420331309 totalMatches 3752 wins 2894 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label claude-opus-5.5 Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/5` |  |  |  |  |
| 6 | [GPT-6 Sol](https://benchize.com/models/gpt-6-sol.md) | 1,402.22elo | CI 1,373.1–1,431.34 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1402.2228602299053 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1VuaG2XLSHlJFZ sourceModelVersion gpt-6-sol weighted false ### Reported statistics Uncertainty Confidence interval: 1,373.1–1,431.34 confidenceIntervalLowerOffset 29.120100199175795 confidenceIntervalUpperOffset 29.120100199176022 totalMatches 3807 wins 2713 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label gpt-6-sol Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/8` |  |  |  |  |
| 7 | [GPT-6 Astra](https://benchize.com/models/gpt-6-astra.md) | 1,356.24elo | CI 1,336.26–1,376.22 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1356.236073065835 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1UTasGEdHyT3rB sourceModelVersion gpt-6-astra weighted false ### Reported statistics Uncertainty Confidence interval: 1,336.26–1,376.22 confidenceIntervalLowerOffset 19.979692916684144 confidenceIntervalUpperOffset 19.979692916683916 totalMatches 7301 wins 4702 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label gpt-6-astra Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/10` |  |  |  |  |
| 8 | [Gemini 3.8 Flash](https://benchize.com/models/gemini-3-8-flash.md) | 1,240.46elo | CI 1,214.71–1,266.2 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1240.4588189756976 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1U5GNxRa1BnOvM sourceModelVersion gemini-3.8-flash weighted false ### Reported statistics Uncertainty Confidence interval: 1,214.71–1,266.2 confidenceIntervalLowerOffset 25.744441846911286 confidenceIntervalUpperOffset 25.744441846911286 totalMatches 4522 wins 2910 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label gemini-3.8-flash Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/12` |  |  |  |  |
| 9 | [Grok 4.7](https://benchize.com/models/grok-4-7.md) | 1,226.22elo | CI 1,191.41–1,261.03 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1226.2208685533628 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1VoMvzV1yVIKJW sourceModelVersion grok-4.7 weighted false ### Reported statistics Uncertainty Confidence interval: 1,191.41–1,261.03 confidenceIntervalLowerOffset 34.81169704105582 confidenceIntervalUpperOffset 34.811697041055595 totalMatches 2330 wins 1385 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label grok-4.7 Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/13` |  |  |  |  |
| 10 | [Gemini 3.7 Flash](https://benchize.com/models/gemini-3-7-flash.md) | 1,206.45elo | CI 1,186.51–1,226.39 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1206.4492382114604 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1SfXSEUZiGlkGa sourceModelVersion gemini-3.7-flash weighted false ### Reported statistics Uncertainty Confidence interval: 1,186.51–1,226.39 confidenceIntervalLowerOffset 19.9400065154407 confidenceIntervalUpperOffset 19.9400065154407 totalMatches 7656 wins 5017.5 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label gemini-3.7-flash Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/14` |  |  |  |  |
| 11 | [Space Bunny Alpha](https://benchize.com/models/space-bunny-alpha.md) | 1,163.55elo | CI 1,135.7–1,191.4 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1163.548976179658 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1W0b2Tvf9I5hb9 sourceModelVersion space-bunny-alpha weighted false ### Reported statistics Uncertainty Confidence interval: 1,135.7–1,191.4 confidenceIntervalLowerOffset 27.853584345987656 confidenceIntervalUpperOffset 27.853584345987656 totalMatches 3655 wins 2157 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label space-bunny-alpha Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/17` |  |  |  |  |
| 12 | [Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1.md) | 1,158.83elo | CI 1,139.81–1,177.84 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1158.8272001418202 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1U5GPfG7E8fC1J sourceModelVersion claude-fable-5.1 weighted false ### Reported statistics Uncertainty Confidence interval: 1,139.81–1,177.84 confidenceIntervalLowerOffset 19.015314386086175 confidenceIntervalUpperOffset 19.015314386086175 totalMatches 7507 wins 4021.5 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label claude-fable-5.1 Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/18` |  |  |  |  |
| 13 | [Muse Spark Open](https://benchize.com/models/muse-spark-open.md) | 1,157.07elo | CI 1,127.22–1,186.93 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1157.0746476882284 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1YQHvUwA1WKcTD sourceModelVersion muse-spark-open weighted false ### Reported statistics Uncertainty Confidence interval: 1,127.22–1,186.93 confidenceIntervalLowerOffset 29.858220943188144 confidenceIntervalUpperOffset 29.858220943188144 totalMatches 3200 wins 1871 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label muse-spark-open Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/19` |  |  |  |  |
| 14 | [Gemini 3.1 Pro Preview](https://benchize.com/models/gemini-3-1-pro-preview.md) | 1,145.27elo | CI 1,130.84–1,159.69 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1145.2653371815616 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1MFl49p61xwRyK sourceModelVersion gemini-3.1-pro-preview weighted false ### Reported statistics Uncertainty Confidence interval: 1,130.84–1,159.69 confidenceIntervalLowerOffset 14.427478595599268 confidenceIntervalUpperOffset 14.427478595599268 totalMatches 15027 wins 9955 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label gemini-3.1-pro-preview Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/20` |  |  |  |  |
| 15 | [Gemini 3.5 Flash](https://benchize.com/models/gemini-3-5-flash.md) | 1,126.11elo | CI 1,111.54–1,140.68 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1126.112178932898 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1MFl7Da7c7ILnh sourceModelVersion gemini-3.5-flash weighted false ### Reported statistics Uncertainty Confidence interval: 1,111.54–1,140.68 confidenceIntervalLowerOffset 14.568453424977406 confidenceIntervalUpperOffset 14.568453424977179 totalMatches 14495 wins 9391.5 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label gemini-3.5-flash Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/23` |  |  |  |  |
| 16 | [GPT-6 Luna](https://benchize.com/models/gpt-6-luna.md) | 1,110.43elo | CI 1,083.67–1,137.19 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1110.4284562959824 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1VuaG6iJYihHJZ sourceModelVersion gpt-6-luna weighted false ### Reported statistics Uncertainty Confidence interval: 1,083.67–1,137.19 confidenceIntervalLowerOffset 26.758072710484612 confidenceIntervalUpperOffset 26.758072710484612 totalMatches 3808 wins 2144 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label gpt-6-luna Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/24` |  |  |  |  |
| 17 | [Claude Fable 5](https://benchize.com/models/claude-fable-5.md) | 1,093.99elo | CI 1,079.43–1,108.55 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1093.9892478981626 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1MFl8sgmdmfb8S sourceModelVersion claude-fable-5 weighted false ### Reported statistics Uncertainty Confidence interval: 1,079.43–1,108.55 confidenceIntervalLowerOffset 14.558848033678714 confidenceIntervalUpperOffset 14.558848033678714 totalMatches 12890 wins 7242 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label claude-fable-5 Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/29` |  |  |  |  |
| 18 | [Claude Opus 5](https://benchize.com/models/claude-opus-5.md) | 1,081.01elo | CI 1,062.41–1,099.62 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1081.014131772095 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1SfXO7B9TVx3E2 sourceModelVersion claude-opus-5 weighted false ### Reported statistics Uncertainty Confidence interval: 1,062.41–1,099.62 confidenceIntervalLowerOffset 18.604382030862325 confidenceIntervalUpperOffset 18.604382030862325 totalMatches 7947 wins 4692.5 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label claude-opus-5 Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/30` |  |  |  |  |
| 19 | [Muse Spark 1.3](https://benchize.com/models/muse-spark-1-3.md) | 1,061.44elo | CI 1,036.94–1,085.94 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1061.4394400231167 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1U5GLtvnzDJIgG sourceModelVersion muse-spark-1.3 weighted false ### Reported statistics Uncertainty Confidence interval: 1,036.94–1,085.94 confidenceIntervalLowerOffset 24.50240864735065 confidenceIntervalUpperOffset 24.50240864735065 totalMatches 4595 wins 2519 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label muse-spark-1.3 Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/31` |  |  |  |  |
| 20 | [Recraft V4.1 Pro Vector](https://benchize.com/models/recraft-v4-1-pro-vector.md) | 928.26elo | CI 902.29–954.23 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 928.2618553139529 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1USVRxipeTnLie sourceModelVersion recraft-v4.1-pro-vector weighted false ### Reported statistics Uncertainty Confidence interval: 902.29–954.23 confidenceIntervalLowerOffset 25.967089491639058 confidenceIntervalUpperOffset 25.967089491638944 totalMatches 4178 wins 1957 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label recraft-v4.1-pro-vector Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/39` |  |  |  |  |
| 21 | [Claude Opus 4.6](https://benchize.com/models/claude-opus-4-6.md) | 925.17elo | CI 911.31–939.02 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 925.1679712382374 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1MFkkvXc8LU68O sourceModelVersion claude-opus-4-6 weighted false ### Reported statistics Uncertainty Confidence interval: 911.31–939.02 confidenceIntervalLowerOffset 13.855808125681847 confidenceIntervalUpperOffset 13.855808125681733 totalMatches 14274 wins 7660 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label claude-opus-4-6 Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/40` |  |  |  |  |
| 22 | [Recraft V4.1 Vector](https://benchize.com/models/recraft-v4-1-vector.md) | 921.05elo | CI 895.25–946.85 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 921.0467660105958 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1USVQ0sk0HX57c sourceModelVersion recraft-v4.1-vector weighted false ### Reported statistics Uncertainty Confidence interval: 895.25–946.85 confidenceIntervalLowerOffset 25.799371866496244 confidenceIntervalUpperOffset 25.799371866496244 totalMatches 4244 wins 1976 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label recraft-v4.1-vector Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/41` |  |  |  |  |
| 23 | [MiniMax M3](https://benchize.com/models/minimax-m3.md) | 907.91elo | CI 893.71–922.12 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 907.91432835456 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1MFltlQRYSJKls sourceModelVersion minimax-m3 weighted false ### Reported statistics Uncertainty Confidence interval: 893.71–922.12 confidenceIntervalLowerOffset 14.20839891829371 confidenceIntervalUpperOffset 14.208398918293597 totalMatches 13515 wins 7021.5 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label minimax-m3 Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/43` |  |  |  |  |
| 24 | [Claude Sonnet 4.6](https://benchize.com/models/claude-sonnet-4-6.md) | 884.03elo | CI 869.46–898.61 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 884.0343968720742 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1MFlFMfOmmSOCS sourceModelVersion claude-sonnet-4.6 weighted false ### Reported statistics Uncertainty Confidence interval: 869.46–898.61 confidenceIntervalLowerOffset 14.576663362370937 confidenceIntervalUpperOffset 14.576663362370823 totalMatches 12727 wins 6354 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label claude-sonnet-4.6 Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/45` |  |  |  |  |
| 25 | [Claude Opus 4.7](https://benchize.com/models/claude-opus-4-7.md) | 882.48elo | CI 865.87–899.08 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 882.4766590295712 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1MFkpiOxkRXc0p sourceModelVersion claude-opus-4-7 weighted false ### Reported statistics Uncertainty Confidence interval: 865.87–899.08 confidenceIntervalLowerOffset 16.605357914145202 confidenceIntervalUpperOffset 16.605357914145316 totalMatches 9702 wins 4617 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label claude-opus-4-7 Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/47` |  |  |  |  |
| 26 | [DeepSeek V4.1 Flash](https://benchize.com/models/deepseek-v4-1-flash.md) | 876.45elo | CI 842.84–910.06 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 876.450192290637 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1Ufa7GRhUiMfuj sourceModelVersion deepseek-v4.1-flash weighted false ### Reported statistics Uncertainty Confidence interval: 842.84–910.06 confidenceIntervalLowerOffset 33.61284234262985 confidenceIntervalUpperOffset 33.61284234262985 totalMatches 2483 wins 1000 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label deepseek-v4.1-flash Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/48` |  |  |  |  |
| 27 | [Claude Opus 4.8](https://benchize.com/models/claude-opus-4-8.md) | 865.86elo | CI 852.01–879.72 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 865.86390887186 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1MFktZvas05x17 sourceModelVersion claude-opus-4-8 weighted false ### Reported statistics Uncertainty Confidence interval: 852.01–879.72 confidenceIntervalLowerOffset 13.856090941915909 confidenceIntervalUpperOffset 13.856090941915795 totalMatches 14114 wins 7077 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label claude-opus-4-8 Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/49` |  |  |  |  |
| 28 | [MiMo-V2.5-Pro](https://benchize.com/models/mimo-v2-5-pro.md) | 844.47elo | CI 829.43–859.5 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 844.4665498816885 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1MFlplt4oURk2R sourceModelVersion mimo-v2.5-pro weighted false ### Reported statistics Uncertainty Confidence interval: 829.43–859.5 confidenceIntervalLowerOffset 15.038127179815547 confidenceIntervalUpperOffset 15.038127179815547 totalMatches 11909 wins 5634.5 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label mimo-v2.5-pro Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/50` |  |  |  |  |
| 29 | [Muse Spark 1.2](https://benchize.com/models/muse-spark-1-2.md) | 840.1elo | CI 820.11–860.08 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 840.0950652713956 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1SfXdIM0YCuNxN sourceModelVersion muse-spark-1.2 weighted false ### Reported statistics Uncertainty Confidence interval: 820.11–860.08 confidenceIntervalLowerOffset 19.984695221310744 confidenceIntervalUpperOffset 19.984695221310744 totalMatches 6872 wins 3076 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label muse-spark-1.2 Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/51` |  |  |  |  |
| 30 | [Ling 3.1 Flash](https://benchize.com/models/ling-3-1-flash.md) | 829.56elo | CI 800.83–858.29 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 829.5602482296808 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1WiuGeiZXt8pTn sourceModelVersion ling-3.1-flash weighted false ### Reported statistics Uncertainty Confidence interval: 800.83–858.29 confidenceIntervalLowerOffset 28.73352572252452 confidenceIntervalUpperOffset 28.73352572252452 totalMatches 3491 wins 1420 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label ling-3.1-flash Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/52` |  |  |  |  |
| 31 | [DeepSeek V4 Pro](https://benchize.com/models/deepseek-v4-pro.md) | 759.56elo | CI 741.84–777.27 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 759.5564448248992 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1MFlMvFnF7SJTw sourceModelVersion deepseek-v4-pro weighted false ### Reported statistics Uncertainty Confidence interval: 741.84–777.27 confidenceIntervalLowerOffset 17.713425544243933 confidenceIntervalUpperOffset 17.713425544243933 totalMatches 8986 wins 3610.5 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label deepseek-v4-pro Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/55` |  |  |  |  |
| 32 | [DeepSeek V4 Flash](https://benchize.com/models/deepseek-v4-flash.md) | 755.01elo | CI 740.66–769.36 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 755.0098901542219 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1MFlJRdB8cayLk sourceModelVersion deepseek-v4-flash weighted false ### Reported statistics Uncertainty Confidence interval: 740.66–769.36 confidenceIntervalLowerOffset 14.347686568107747 confidenceIntervalUpperOffset 14.347686568107747 totalMatches 13603 wins 5922.5 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label deepseek-v4-flash Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/56` |  |  |  |  |
| 33 | [Claude Sonnet 5](https://benchize.com/models/claude-sonnet-5.md) | 730.49elo | CI 704.97–756.01 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 730.4887351124103 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1U5GREiZ6VzNob sourceModelVersion claude-sonnet-5 weighted false ### Reported statistics Uncertainty Confidence interval: 704.97–756.01 confidenceIntervalLowerOffset 25.52172843468304 confidenceIntervalUpperOffset 25.52172843468304 totalMatches 4380 wins 1598.5 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label claude-sonnet-5 Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/58` |  |  |  |  |
| 34 | [Grok 4.20 Multi Agent](https://benchize.com/models/grok-4-20-multi-agent.md) | 683.25elo | CI 665.67–700.84 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 683.2542880320492 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1MFlbUFhJTV88K sourceModelVersion grok-4.20-multi-agent weighted false ### Reported statistics Uncertainty Confidence interval: 665.67–700.84 confidenceIntervalLowerOffset 17.589260023243696 confidenceIntervalUpperOffset 17.58926002324381 totalMatches 9333 wins 3381 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label grok-4.20-multi-agent Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/59` |  |  |  |  |
| 35 | [Grok 4.6](https://benchize.com/models/grok-4-6.md) | 646.86elo | CI 626.39–667.32 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 646.8573512979482 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1SfXZfBU6YOfT0 sourceModelVersion grok-4.6 weighted false ### Reported statistics Uncertainty Confidence interval: 626.39–667.32 confidenceIntervalLowerOffset 20.46363825131516 confidenceIntervalUpperOffset 20.46363825131516 totalMatches 7098 wins 2452 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label grok-4.6 Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/60` |  |  |  |  |
| 36 | [Mistral Large 3](https://benchize.com/models/mistral-large-3.md) | 277.67elo | CI 255.1–300.23 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 277.66730406688873 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1MFm6FUSnthmKA sourceModelVersion mistral-large-3 weighted false ### Reported statistics Uncertainty Confidence interval: 255.1–300.23 confidenceIntervalLowerOffset 22.5634355580047 confidenceIntervalUpperOffset 22.5634355580047 totalMatches 8594 wins 1541 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label mistral-large-3 Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/66` |  |  |  |  |
| 37 | [Mistral Medium 3.5](https://benchize.com/models/mistral-medium-3-5.md) | 234.61elo | CI 213.98–255.24 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 234.60724490699238 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1MFmBWcCBCPu35 sourceModelVersion mistral-medium-3.5 weighted false ### Reported statistics Uncertainty Confidence interval: 213.98–255.24 confidenceIntervalLowerOffset 20.628026047171033 confidenceIntervalUpperOffset 20.628026047171033 totalMatches 10962 wins 1889 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label mistral-medium-3.5 Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/67` |  |  |  |  |

---
Cite as: Rapidata SVG generation — Preference — Benchize, https://benchize.com/benchmarks/rapidata%3Asvg%3Arlb_1MFkkEMFnCNyKl (retrieved 2026-10-21)