# Claude Opus 5

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

Anthropic

Canonical URL: https://benchize.com/models/claude-opus-5
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.

Anthropic

## Benchmarks

| Benchmark | Score | ± | Rank | Cost | Latency | Source |  |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [DesignArena Agentic presentation generation](https://benchize.com/benchmarks/designarena%3Aagentic-slides.md) | 1,265elo | SE ±14.34 | 3 / 19 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=agentic-slides) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1265 \| elo \| agentic-slides \| Higher is better \| ### Configuration arenaType agents category agon_slides inputModality Not reported sourceModelVersion claude-opus-5 variationName public ### Reported statistics Uncertainty Standard error: ±14.34 averageGenerationTimeMs Not reported battles 608 losses 278 standardError 14.3381 winRate 54.3 wins 330 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=agentic-slides) Source designarena Original model label Claude Opus 5 Source version public Observed 2026-10-21T16:38:03.963Z Evidence SHA-256 `b732c5aba2e357cf6034f23084d5f95f8e8882f62b8bf3ee340f0cd5cd773724` Source locator `/data/3` |  |  |  |  |  |  |  |
| [SimpleBench](https://benchize.com/benchmarks/simplebench%3Aavg-at-5.md) | 80.6% | — | 7 / 62 | — | — | [simplebench](https://simple-bench.com/static/js/leaderboard-data.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 80.6 \| percent \| average_at_5 \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude Opus 5 thinkingEnabled Not reported ### Reported statistics rank 9th ### Source [Original source](https://simple-bench.com/static/js/leaderboard-data.js) Source simplebench Original model label Claude Opus 5 Observed 2026-10-21T16:32:13.183Z Evidence SHA-256 `b2d0285ad3e4e15750ed20d39897e7558d1c05e8962e90c861b06f93c8019dc9` Source locator `/rows/10` |  |  |  |  |  |  |  |
| [CorpFin v2 / overall](https://benchize.com/benchmarks/vals-ai%3Acorp_fin_v2%3Aoverall.md) | 73.19% | SE ±0.87 pp | 1 / 39 | $0.86 | 28.57source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_corp_fin_v2.CectKwl1.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 73.194 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.860452 \| USD \| per_test \| Lower is better \| \| `latency` \| 28.573 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider Anthropic reasoning Not reported Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.87 pp sourcePopulation 134 stderr 0.871 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_corp_fin_v2.CectKwl1.json) Source Vals AI Original model label anthropic/claude-opus-5 Source version 2 Observed 2026-10-21T16:45:57.998Z Evidence SHA-256 `7cf2217ab3728d5a84bffce82aab9fc52d7f810b0cbe8c65b387df47f3d31c9b` Source locator `/tasks/overall/anthropic~1claude-opus-5` |  |  |  |  |  |  |  |
| [DesignArena Browser game generation](https://benchize.com/benchmarks/designarena%3Agame-dev.md) | 1,338elo | — | 11 / 117 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=game-dev) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1338 \| elo \| game-dev \| Higher is better \| ### Configuration arenaType models category gamedev inputModality Not reported sourceModelVersion claude-opus-5 variationName public ### Reported statistics averageGenerationTimeMs 394395 battles 3068 losses 1275 standardError Not reported winRate 58.4 wins 1793 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=game-dev) Source designarena Original model label Claude Opus 5 Source version public Observed 2026-10-21T16:38:01.100Z Evidence SHA-256 `53db6a89112ce8cdf644568c666d4b8309aece764cfcedb291ffd52ae3934e30` Source locator `/data/12` |  |  |  |  |  |  |  |
| [DesignArena Native Android development](https://benchize.com/benchmarks/designarena%3Aandroid.md) | 1,260elo | — | 2 / 23 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=android) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1260 \| elo \| android \| Higher is better \| ### Configuration arenaType agents category nativeapps inputModality Not reported sourceModelVersion claude-opus-5 variationName public ### Reported statistics averageGenerationTimeMs Not reported battles 393 losses 174 standardError Not reported winRate 55.7 wins 219 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=android) Source designarena Original model label Claude Opus 5 Source version public Observed 2026-10-21T16:38:03.000Z Evidence SHA-256 `d9d0cd4bea54b696c28f907a98ba42ebf8dd4da9da201b6c70c95f76de35f525` Source locator `/data/2` |  |  |  |  |  |  |  |
| [DesignArena Full-stack application development](https://benchize.com/benchmarks/designarena%3Afullstack.md) | 1,306elo | SE ±10.77 | 3 / 31 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=fullstack) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1306 \| elo \| fullstack \| Higher is better \| ### Configuration arenaType agents category fullstack inputModality Not reported sourceModelVersion claude-opus-5 variationName public ### Reported statistics Uncertainty Standard error: ±10.77 averageGenerationTimeMs Not reported battles 1195 losses 510 standardError 10.7707 winRate 57.3 wins 685 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=fullstack) Source designarena Original model label Claude Opus 5 Source version public Observed 2026-10-21T16:38:00.857Z Evidence SHA-256 `aa171459dd44cfad57fba8da746c40b27832b57dc731b1198bdb71c73ddd0f97` Source locator `/data/4` |  |  |  |  |  |  |  |
| [DesignArena ASCII art generation](https://benchize.com/benchmarks/designarena%3Aascii.md) | 1,352elo | — | 2 / 65 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=ascii) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1352 \| elo \| ascii \| Higher is better \| ### Configuration arenaType models category ascii inputModality Not reported sourceModelVersion claude-opus-5 variationName public ### Reported statistics averageGenerationTimeMs 246414 battles 227 losses 74 standardError Not reported winRate 67.4 wins 153 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ascii) Source designarena Original model label Claude Opus 5 Source version public Observed 2026-10-21T16:38:03.513Z Evidence SHA-256 `0603b8c65b44ee887f5b566feb469465f59635137a6ac5c6d94c23bcf3776311` Source locator `/data/1` |  |  |  |  |  |  |  |
| [OTIS Mock AIME 2024–2025](https://benchize.com/benchmarks/epoch-ai%3Aotis_mock_aime_2024_2025.md) | 97.78% | SE ±2.22 pp | 22 / 123 | — | — | [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` \| 0.9777777777777777 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.9777777777777777 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion OTIS Mock AIME 2024-2025 reasoningBudget Not reported Reasoning effort Not reported sourceModelVersion claude-opus-5 ### Reported statistics Uncertainty Standard error: ±2.22 pp standardError 0.022222222222222223 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=otis_mock_aime_2024_2025.csv) Source epoch ai Original model label claude-opus-5 Source version OTIS Mock AIME 2024-2025 Evaluated 2026-08-06T22:21:15.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `5b411612f91e155dff4b09d09b548b42f7936482ea8b3c00b510bd46e2f6bc2c` Source locator `/rows/131` |  |  |  |  |  |  |  |
| [SWE-bench / 1-4 hours](https://benchize.com/benchmarks/vals-ai%3Aswebench%3A1-4%20hours.md) | 90.48% | SE ±4.58 pp | 5 / 39 | $2.29 | 842.26source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 90.476 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.291537 \| USD \| per_test \| Lower is better \| \| `latency` \| 842.258 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider Anthropic reasoning Not reported Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.58 pp sourcePopulation 88 stderr 4.584 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label anthropic/claude-opus-5 Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/1-4 hours/anthropic~1claude-opus-5` |  |  |  |  |  |  |  |
| [NC Bench](https://benchize.com/benchmarks/nc-bench%3Aoverall.md) | 89.97% | — | 60 / 144 | — | — | [nc bench](https://www.nc-bench.com/models) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 89.97 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.77 \| percent \| category \| Higher is better \| \| `creative_writing` \| 88.13 \| percent \| category \| Higher is better \| \| `language` \| 99.73 \| percent \| category \| Higher is better \| \| `utility` \| 90.5 \| percent \| category \| Higher is better \| \| `reasoning` \| 85.64 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.06 \| percent \| category \| Higher is better \| \| `rule_following` \| 64.01 \| percent \| category \| Higher is better \| \| `hallucination` \| 93.91 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude Opus 5 thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Claude Opus 5 Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/74` |  |  |  |  |  |  |  |
| [HiL-Bench (Human-in-Loop Benchmark)](https://benchize.com/benchmarks/scale%3Ahil.md) | 57source score | CI 51.52–62.48 | 7 / 22 | — | — | [scale](https://labs.scale.com/leaderboard/hil) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 57 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude Opus 5 sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 51.52–62.48 contaminationWarning Not reported rank 10 reportedConfidenceHalfWidth 5.48 ### Source [Original source](https://labs.scale.com/leaderboard/hil) Source scale Original model label Claude Opus 5 Observed 2026-10-21T16:35:30.082Z Evidence SHA-256 `043a333e27453edada150667c7f4439b2aab463f37928c2153c6aa79f33dd1b2` Source locator `/rows/9` |  |  |  |  |  |  |  |
| [Vibe Code Bench v1.1 / overall](https://benchize.com/benchmarks/vals-ai%3Avibe-code%3Aoverall.md) | 88.4% | SE ±3 pp | 9 / 59 | $33.88 | 5,301.22source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_vibe_code_bench.DcEBMbCA.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 88.404 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 33.876235 \| USD \| per_test \| Lower is better \| \| `latency` \| 5301.22 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness OpenHands maxOutputTokens Not reported provider Anthropic reasoning Not reported Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3 pp sourcePopulation 116 stderr 3.001 tokenTotals {"cache_read_tokens":2470549366,"cache_write_tokens":35417005,"input_tokens":2505984639,"output_tokens":9909555,"reasoning_tokens":1547105} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vibe_code_bench.DcEBMbCA.json) Source Vals AI Original model label anthropic/claude-opus-5 Source version 1.1 Observed 2026-10-21T16:46:08.625Z Evidence SHA-256 `0e8c23f521a0f751c5592952620e197b376cade41c78578461b7aa5740a173e7` Source locator `/tasks/overall/anthropic~1claude-opus-5` |  |  |  |  |  |  |  |
| [Rapidata SVG generation — Coherence](https://benchize.com/benchmarks/rapidata%3Asvg%3Arlb_1MFkkBzpuU8fTG.md) | 1,081.36elo | CI 1,063.51–1,099.21 | 10 / 37 | — | — | [rapidata · v1](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkBzpuU8fTG) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1081.3606930666897 \| elo \| rlb_1MFkkBzpuU8fTG \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkBzpuU8fTG participantId par_1SfXO7B9TVx3E2 sourceModelVersion claude-opus-5 weighted false ### Reported statistics Uncertainty Confidence interval: 1,063.51–1,099.21 confidenceIntervalLowerOffset 17.8527012292559 confidenceIntervalUpperOffset 17.8527012292559 totalMatches 7947 wins 4430.5 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkBzpuU8fTG) Source rapidata Original model label claude-opus-5 Source version v1 Observed 2026-10-21T16:37:39.715Z Evidence SHA-256 `aa3cb94ff16f544c58adeea35b9087d281c785058b8ce1ae0f98a7ff84920930` Source locator `/items/21` |  |  |  |  |  |  |  |
| [Vals Multimodal Index / swebench](https://benchize.com/benchmarks/vals-ai%3Avals_multimodal_index%3Aswebench.md) | 95.1% | SE ±2.14 pp | 3 / 20 | $1.55 | 665.89source duration | [Vals AI · 1.2](https://www.vals.ai/_astro/benchmark_view_vals_multimodal_index.virVpWMs.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 95.098 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.554764 \| USD \| per_test \| Lower is better \| \| `latency` \| 665.89 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider Not reported reasoning Not reported Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.14 pp sourcePopulation 33 stderr 2.138 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_multimodal_index.virVpWMs.json) Source Vals AI Original model label anthropic/claude-opus-5 Source version 1.2 Observed 2026-10-21T16:45:51.881Z Evidence SHA-256 `077b22575f6e075b7b78157d000ec8f94d7ead409c7dcbcf04887630ed572a2d` Source locator `/tasks/swebench/anthropic~1claude-opus-5` |  |  |  |  |  |  |  |
| [MortgageTax / numerical extraction](https://benchize.com/benchmarks/vals-ai%3Amortgage_tax%3Anumerical_extraction.md) | 81.4% | SE ±1.1 pp | 1 / 31 | $0.07 | 8.48source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mortgage_tax.DCd-oO5Y.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 81.399 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.074778 \| USD \| per_test \| Lower is better \| \| `latency` \| 8.479 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider Anthropic reasoning Not reported Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.1 pp sourcePopulation 98 stderr 1.097 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mortgage_tax.DCd-oO5Y.json) Source Vals AI Original model label anthropic/claude-opus-5 Source version 1 Observed 2026-10-21T16:45:58.500Z Evidence SHA-256 `e5c844561f97d119d66d70269e726ecfb68be79eae39acf14ead3e95422e648c` Source locator `/tasks/numerical_extraction/anthropic~1claude-opus-5` |  |  |  |  |  |  |  |
| [DesignArena Agentic game development](https://benchize.com/benchmarks/designarena%3Aagentic-game-dev.md) | 1,261elo | SE ±12.65 | 3 / 17 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=agentic-game-dev) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1261 \| elo \| agentic-game-dev \| Higher is better \| ### Configuration arenaType agents category agentic_gamedev inputModality Not reported sourceModelVersion claude-opus-5 variationName public ### Reported statistics Uncertainty Standard error: ±12.65 averageGenerationTimeMs Not reported battles 787 losses 363 standardError 12.6545 winRate 53.9 wins 424 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=agentic-game-dev) Source designarena Original model label Claude Opus 5 Source version public Observed 2026-10-21T16:38:01.564Z Evidence SHA-256 `2bb291527289cec897df421c3c59427ce53230a312bf61790ba7ac6ca436bb4b` Source locator `/data/2` |  |  |  |  |  |  |  |
| [DesignArena Godot game development](https://benchize.com/benchmarks/designarena%3Agodot-game-dev.md) | 1,279elo | SE ±13.52 | 4 / 14 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=godot-game-dev) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1279 \| elo \| godot-game-dev \| Higher is better \| ### Configuration arenaType agents category agon_godot inputModality Not reported sourceModelVersion claude-opus-5 variationName public ### Reported statistics Uncertainty Standard error: ±13.52 averageGenerationTimeMs Not reported battles 793 losses 363 standardError 13.5177 winRate 54.2 wins 430 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=godot-game-dev) Source designarena Original model label Claude Opus 5 Source version public Observed 2026-10-21T16:38:02.075Z Evidence SHA-256 `0aad65341ae5287f97ba93448674c557edad76a4e41056ec30cc32bf05d3a7e3` Source locator `/data/3` |  |  |  |  |  |  |  |
| [SWE-bench / 15 min - 1 hour](https://benchize.com/benchmarks/vals-ai%3Aswebench%3A15%20min%20-%201%20hour.md) | 96.94% | SE ±1.07 pp | 1 / 39 | $1.41 | 638.83source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 96.935 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.409354 \| USD \| per_test \| Lower is better \| \| `latency` \| 638.832 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider Anthropic reasoning Not reported Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.07 pp sourcePopulation 88 stderr 1.069 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label anthropic/claude-opus-5 Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/15 min - 1 hour/anthropic~1claude-opus-5` |  |  |  |  |  |  |  |
| [CorpFin v2 / exact pages](https://benchize.com/benchmarks/vals-ai%3Acorp_fin_v2%3Aexact_pages.md) | 68.65% | SE ±1.58 pp | 1 / 39 | $0.04 | 16.03source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_corp_fin_v2.CectKwl1.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 68.648 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.044928 \| USD \| per_test \| Lower is better \| \| `latency` \| 16.028 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider Anthropic reasoning Not reported Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.58 pp sourcePopulation 134 stderr 1.584 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_corp_fin_v2.CectKwl1.json) Source Vals AI Original model label anthropic/claude-opus-5 Source version 2 Observed 2026-10-21T16:45:57.998Z Evidence SHA-256 `7cf2217ab3728d5a84bffce82aab9fc52d7f810b0cbe8c65b387df47f3d31c9b` Source locator `/tasks/exact_pages/anthropic~1claude-opus-5` |  |  |  |  |  |  |  |
| [Rapidata SVG generation — Alignment](https://benchize.com/benchmarks/rapidata%3Asvg%3Arlb_1MFkk9yZHssERh.md) | 1,083.77elo | CI 1,064.93–1,102.6 | 19 / 37 | — | — | [rapidata · v1](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkk9yZHssERh) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1083.7679809948331 \| elo \| rlb_1MFkk9yZHssERh \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkk9yZHssERh participantId par_1SfXO7B9TVx3E2 sourceModelVersion claude-opus-5 weighted false ### Reported statistics Uncertainty Confidence interval: 1,064.93–1,102.6 confidenceIntervalLowerOffset 18.836356413705744 confidenceIntervalUpperOffset 18.836356413705744 totalMatches 7881 wins 4632 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkk9yZHssERh) Source rapidata Original model label claude-opus-5 Source version v1 Observed 2026-10-21T16:37:40.342Z Evidence SHA-256 `2f5c8d08728735790b500d930d71b66f04253f1209f7c1c3da0db0846c163fcf` Source locator `/items/32` |  |  |  |  |  |  |  |
| [MortgageTax / semantic extraction](https://benchize.com/benchmarks/vals-ai%3Amortgage_tax%3Asemantic_extraction.md) | 62.72% | SE ±1.36 pp | 2 / 31 | $0.07 | 7.48source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mortgage_tax.DCd-oO5Y.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 62.719 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.072722 \| USD \| per_test \| Lower is better \| \| `latency` \| 7.477 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider Anthropic reasoning Not reported Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.36 pp sourcePopulation 98 stderr 1.363 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mortgage_tax.DCd-oO5Y.json) Source Vals AI Original model label anthropic/claude-opus-5 Source version 1 Observed 2026-10-21T16:45:58.500Z Evidence SHA-256 `e5c844561f97d119d66d70269e726ecfb68be79eae39acf14ead3e95422e648c` Source locator `/tasks/semantic_extraction/anthropic~1claude-opus-5` |  |  |  |  |  |  |  |
| [FrontierSWE v2 abs](https://benchize.com/benchmarks/frontierswe%3Av2%3Aabs.md) | 52.01source score | — | 5 / 15 | — | — | [frontierswe](https://www.frontierswe.com/) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `overall` \| 52.01176764705882 \| source_score \| mean \| Higher is better \| \| `overall_best` \| 60.6518411764706 \| source_score \| best \| Higher is better \| \| `overall_worst` \| 39.12135000000001 \| source_score \| worst \| Higher is better \| \| `implementation` \| 70.52801000000001 \| source_score \| mean \| Higher is better \| \| `performance` \| 37.79192666666666 \| source_score \| mean \| Higher is better \| \| `research` \| 42.491305714285716 \| source_score \| mean \| Higher is better \| ### Configuration aggregation mean harness proximus normalization abs Reasoning effort unknown ### Source [Original source](https://www.frontierswe.com/) Source frontierswe Original model label Claude Opus 5 Observed 2026-10-21T16:31:27.602Z Evidence SHA-256 `818e027068cf61ff1aadd8281b6e49e9c6795221015210601b5e34d0d223e5b5` Source locator `/rows/4` |  |  |  |  |  |  |  |
| [Rapidata SVG generation — Preference](https://benchize.com/benchmarks/rapidata%3Asvg%3Arlb_1MFkkEMFnCNyKl.md) | 1,081.01elo | CI 1,062.41–1,099.62 | 18 / 37 | — | — | [rapidata · v1](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) |  |
| ### 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` |  |  |  |  |  |  |  |
| [Vals Multimodal Index / overall](https://benchize.com/benchmarks/vals-ai%3Avals_multimodal_index%3Aoverall.md) | 73.9% | SE ±1.24 pp | 2 / 20 | $6.14 | 853.76source duration | [Vals AI · 1.2](https://www.vals.ai/_astro/benchmark_view_vals_multimodal_index.virVpWMs.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 73.896 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.136905 \| USD \| per_test \| Lower is better \| \| `latency` \| 853.761 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider Anthropic reasoning Not reported Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.24 pp sourcePopulation 33 stderr 1.243 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_multimodal_index.virVpWMs.json) Source Vals AI Original model label anthropic/claude-opus-5 Source version 1.2 Observed 2026-10-21T16:45:51.881Z Evidence SHA-256 `077b22575f6e075b7b78157d000ec8f94d7ead409c7dcbcf04887630ed572a2d` Source locator `/tasks/overall/anthropic~1claude-opus-5` |  |  |  |  |  |  |  |
| [Longform Creative Writing](https://benchize.com/benchmarks/eq-bench%3Alongform-writing.md) | 86.3% | — | 1 / 93 | — | — | [eq bench · longform-writing](https://eqbench.com/creative_writing_longform.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `overall_score_100` \| 86.3 \| percent \| overall \| Higher is better \| \| `chapter1_avg` \| 17.51 \| rubric_score \| overall \| Higher is better \| \| `chapter2_avg` \| 17.32 \| rubric_score \| overall \| Higher is better \| \| `chapter3_avg` \| 17.39 \| rubric_score \| overall \| Higher is better \| \| `chapter4_avg` \| 17.45 \| rubric_score \| overall \| Higher is better \| \| `chapter5_avg` \| 17.55 \| rubric_score \| overall \| Higher is better \| \| `chapter6_avg` \| 17.65 \| rubric_score \| overall \| Higher is better \| \| `chapter7_avg` \| 17.79 \| rubric_score \| overall \| Higher is better \| \| `chapter8_avg` \| 18.04 \| rubric_score \| overall \| Higher is better \| \| `final_judgement_avg` \| 17.78 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol longform-writing sourceModelVersion claude-opus-5 ### Source [Original source](https://eqbench.com/creative_writing_longform.js) Source eq bench Original model label claude-opus-5 Source version longform-writing Observed 2026-10-21T16:35:02.575Z Evidence SHA-256 `3ba283ce357ac7620e16db640a961879c30fe3ddc50a27de9a8ed4290784825c` Source locator `/leaderboardDataLongformV3/123` |  |  |  |  |  |  |  |
| [DesignArena Data visualization generation](https://benchize.com/benchmarks/designarena%3Adata-viz.md) | 1,329elo | — | 10 / 99 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=data-viz) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1329 \| elo \| data-viz \| Higher is better \| ### Configuration arenaType models category dataviz inputModality Not reported sourceModelVersion claude-opus-5 variationName public ### Reported statistics averageGenerationTimeMs 225198 battles 1770 losses 740 standardError Not reported winRate 58.2 wins 1030 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=data-viz) Source designarena Original model label Claude Opus 5 Source version public Observed 2026-10-21T16:37:58.264Z Evidence SHA-256 `a895f6f1a25fa8eb01f821c2097ddec4f884de7bd22f1b8a22e82e6679b71849` Source locator `/data/10` |  |  |  |  |  |  |  |
| [Humanity's Last Exam (Diamond)](https://benchize.com/benchmarks/scale%3Ahle-diamond.md) | 38.6source score | CI 35.6–41.6 | 5 / 12 | — | — | [scale](https://labs.scale.com/leaderboard/hle-diamond) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 38.6 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration claude-opus-5 sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 35.6–41.6 contaminationWarning Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions. rank 5 reportedConfidenceHalfWidth 3 ### Source [Original source](https://labs.scale.com/leaderboard/hle-diamond) Source scale Original model label claude-opus-5 Observed 2026-10-21T16:35:27.820Z Evidence SHA-256 `c60d42f5aacdf787d9ccc8b70817766d86707776a7f8b44ef0337cb9ae60bf20` Source locator `/rows/4` |  |  |  |  |  |  |  |
| [OpenVibeEval Accessibility](https://benchize.com/benchmarks/openvibeeval%3Aaccessibility.md) | 80 | — | 5 / 26 | — | — | [openvibeeval](https://openvibeeval.com/leaderboard/) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `adjusted_score` \| 80 \| score \| sample_size_adjusted_accessibility \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude Opus 5 thinkingEnabled Not reported ### Reported statistics runCount 9 ### Source [Original source](https://openvibeeval.com/leaderboard/) Source openvibeeval Original model label Claude Opus 5 Evaluated 2026-08-14 Observed 2026-10-21T16:32:04.885Z Evidence SHA-256 `9b2e7d6060910e3dc7083a6a7f67377601ce78806b2b6b7693cf8d047dd63fbb` Source locator `/rows/3` |  |  |  |  |  |  |  |
| [OfficeQA Pro V2 — Agent Harness](https://benchize.com/benchmarks/officeqa-pro%3Av2-agent.md) | 54.4% | — | 1 / 7 | — | — | [officeqa pro · sha256:d97762a15ad277575c2f567c4e3a318b6bb1d4e4d4d0008cd4f5c7953bae3253](https://api.github.com/repos/databricks/officeqa/git/blobs/cebf9bca23960fa1328f3421f0cb28d236cd86eb) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `correctness` \| 54.4 \| percent \| agent_full_tools \| Higher is better \| ### Configuration harness Anthropic Claude Code ### Reported statistics sampleSize 90 ### Source [Original source](https://api.github.com/repos/databricks/officeqa/git/blobs/cebf9bca23960fa1328f3421f0cb28d236cd86eb) Source officeqa pro Original model label Claude Opus 5 Source version sha256:d97762a15ad277575c2f567c4e3a318b6bb1d4e4d4d0008cd4f5c7953bae3253 Observed 2026-10-21T16:34:42.395Z Evidence SHA-256 `0e566748b11c0bfc76d6076b7d871f45fe43266e4787dfe523c359f3db0b7a10` Source locator `/chart-labels/6` |  |  |  |  |  |  |  |
| [Creative Writing v3](https://benchize.com/benchmarks/eq-bench%3Acreative-writing-v3.md) | 2,132.6elo | — | 3 / 90 | — | — | [eq bench · creative-writing-v3](https://eqbench.com/creative_writing.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 2132.6 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 17.07 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion claude-opus-5 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label claude-opus-5 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/2` |  |  |  |  |  |  |  |
| [Vals Multimodal Index / finance agent](https://benchize.com/benchmarks/vals-ai%3Avals_multimodal_index%3Afinance_agent.md) | 56.57% | SE ±0.44 pp | 4 / 20 | $5.46 | 563.72source duration | [Vals AI · 1.2](https://www.vals.ai/_astro/benchmark_view_vals_multimodal_index.virVpWMs.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 56.57 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 5.463988 \| USD \| per_test \| Lower is better \| \| `latency` \| 563.724 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider Anthropic reasoning Not reported Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.44 pp sourcePopulation 33 stderr 0.443 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_multimodal_index.virVpWMs.json) Source Vals AI Original model label anthropic/claude-opus-5 Source version 1.2 Observed 2026-10-21T16:45:51.881Z Evidence SHA-256 `077b22575f6e075b7b78157d000ec8f94d7ead409c7dcbcf04887630ed572a2d` Source locator `/tasks/finance_agent/anthropic~1claude-opus-5` |  |  |  |  |  |  |  |
| [EQ-Bench 4](https://benchize.com/benchmarks/eq-bench%3Aeqbench4.md) | 1,385elo | CI 1,362.4–1,412 | 1 / 26 | — | — | [eq bench · eqbench4](https://eqbench.com/eqbench4/eqbench4_data.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1385 \| elo \| overall \| Higher is better \| ### Configuration protocol eqbench4 ### Reported statistics Uncertainty Confidence interval: 1,362.4–1,412 confidenceIntervalHigh 1412 confidenceIntervalLow 1362.4 scenarios 120 ### Source [Original source](https://eqbench.com/eqbench4/eqbench4_data.js) Source eq bench Original model label claude-opus-5 Source version eqbench4 Observed 2026-10-21T16:35:00.261Z Evidence SHA-256 `188d8ea4a393978063a6c24dff6c92ce185169827038bfa558091212a68c29d8` Source locator `/models/0` |  |  |  |  |  |  |  |
| [SWE-bench / overall](https://benchize.com/benchmarks/vals-ai%3Aswebench%3Aoverall.md) | 97% | SE ±0.76 pp | 1 / 39 | $1.29 | 576.99source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 97 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.290782 \| USD \| per_test \| Lower is better \| \| `latency` \| 576.988 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider Anthropic reasoning Not reported Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.76 pp sourcePopulation 88 stderr 0.764 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label anthropic/claude-opus-5 Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/overall/anthropic~1claude-opus-5` |  |  |  |  |  |  |  |
| [OfficeQA Pro — Agent Harness](https://benchize.com/benchmarks/officeqa-pro%3Aagent.md) | 60.9% | — | 1 / 13 | — | — | [officeqa pro · sha256:07c23a70c189c84ab808067929402d3b636ce81e46520faca981a178e02065ad](https://api.github.com/repos/databricks/officeqa/git/blobs/125bf765bb37397a7a6b41a49ea04e6117eb95b8) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `correctness` \| 60.9 \| percent \| agent_full_tools \| Higher is better \| ### Configuration harness Claude Agent SDK ### Reported statistics sampleSize 133 ### Source [Original source](https://api.github.com/repos/databricks/officeqa/git/blobs/125bf765bb37397a7a6b41a49ea04e6117eb95b8) Source officeqa pro Original model label Claude Opus 5 Source version sha256:07c23a70c189c84ab808067929402d3b636ce81e46520faca981a178e02065ad Observed 2026-10-21T16:34:41.697Z Evidence SHA-256 `094af719408a1dea8ccb110965da3cc1b83056de87ba0b95e99bf603955f42b1` Source locator `/chart-labels/12` |  |  |  |  |  |  |  |
| [Vals Multimodal Index / mortgage tax](https://benchize.com/benchmarks/vals-ai%3Avals_multimodal_index%3Amortgage_tax.md) | 72.06% | SE ±0.88 pp | 1 / 20 | $0.07 | 7.98source duration | [Vals AI · 1.2](https://www.vals.ai/_astro/benchmark_view_vals_multimodal_index.virVpWMs.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 72.059 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.07375 \| USD \| per_test \| Lower is better \| \| `latency` \| 7.978 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider Anthropic reasoning Not reported Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.88 pp sourcePopulation 33 stderr 0.875 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_multimodal_index.virVpWMs.json) Source Vals AI Original model label anthropic/claude-opus-5 Source version 1.2 Observed 2026-10-21T16:45:51.881Z Evidence SHA-256 `077b22575f6e075b7b78157d000ec8f94d7ead409c7dcbcf04887630ed572a2d` Source locator `/tasks/mortgage_tax/anthropic~1claude-opus-5` |  |  |  |  |  |  |  |
| [CorpFin v2 / max fitting context](https://benchize.com/benchmarks/vals-ai%3Acorp_fin_v2%3Amax_fitting_context.md) | 75.99% | SE ±1.46 pp | 2 / 39 | $1.84 | 40.66source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_corp_fin_v2.CectKwl1.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 75.991 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.839482 \| USD \| per_test \| Lower is better \| \| `latency` \| 40.655 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider Anthropic reasoning Not reported Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.46 pp sourcePopulation 134 stderr 1.458 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_corp_fin_v2.CectKwl1.json) Source Vals AI Original model label anthropic/claude-opus-5 Source version 2 Observed 2026-10-21T16:45:57.998Z Evidence SHA-256 `7cf2217ab3728d5a84bffce82aab9fc52d7f810b0cbe8c65b387df47f3d31c9b` Source locator `/tasks/max_fitting_context/anthropic~1claude-opus-5` |  |  |  |  |  |  |  |
| [TubeLab Scriptwriting](https://benchize.com/benchmarks/tubelab%3Ascriptwriting.md) | 87.9% | — | 1 / 16 | 1.82ratio | — | [tubelab](https://tubelab.net/_next/static/chunks/pages/benchmark/scriptwriting-7ad7196ff3093ad4.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `quality` \| 87.9 \| percent \| source_reported \| Higher is better \| \| `craft` \| 87.9 \| percent \| source_reported \| Higher is better \| \| `relative_cost_per_script` \| 1.82 \| ratio \| source_reported \| Lower is better \| \| `script_time` \| 8.3 \| minutes \| source_reported \| Lower is better \| \| `hook` \| 8.7 \| score_out_of_10 \| craft_rubric \| Higher is better \| \| `retention` \| 8.8 \| score_out_of_10 \| craft_rubric \| Higher is better \| \| `storytelling` \| 8.5 \| score_out_of_10 \| craft_rubric \| Higher is better \| \| `voiceMatch` \| 8.4 \| score_out_of_10 \| craft_rubric \| Higher is better \| \| `pacing` \| 8.8 \| score_out_of_10 \| craft_rubric \| Higher is better \| \| `clarity` \| 9.4 \| score_out_of_10 \| craft_rubric \| Higher is better \| ### Configuration judgingProtocol blind_model_judges Reasoning effort unknown taskCount 12 ### Reported statistics confidence {"high":89.7,"low":85.8} headToHead {"losses":2,"ties":3,"winPercent":65,"wins":7} rank 1 ### Source [Original source](https://tubelab.net/_next/static/chunks/pages/benchmark/scriptwriting-7ad7196ff3093ad4.js) Source tubelab Original model label Claude Opus 5 Observed 2026-10-21T16:34:03.856Z Evidence SHA-256 `72f9d867f388256af8fc6dca12e8c7b6f1ddcbb97f0712da339b73102686761f` Source locator `/rows/0` |  |  |  |  |  |  |  |
| [MortgageTax / overall](https://benchize.com/benchmarks/vals-ai%3Amortgage_tax%3Aoverall.md) | 72.06% | SE ±0.88 pp | 1 / 31 | $0.07 | 7.98source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mortgage_tax.DCd-oO5Y.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 72.059 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.07375 \| USD \| per_test \| Lower is better \| \| `latency` \| 7.978 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider Anthropic reasoning Not reported Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.88 pp sourcePopulation 98 stderr 0.875 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mortgage_tax.DCd-oO5Y.json) Source Vals AI Original model label anthropic/claude-opus-5 Source version 1 Observed 2026-10-21T16:45:58.500Z Evidence SHA-256 `e5c844561f97d119d66d70269e726ecfb68be79eae39acf14ead3e95422e648c` Source locator `/tasks/overall/anthropic~1claude-opus-5` |  |  |  |  |  |  |  |
| [DesignArena Image to HTML](https://benchize.com/benchmarks/designarena%3Aimage-to-html.md) | 1,206elo | — | 22 / 35 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=image-to-html) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1206 \| elo \| image-to-html \| Higher is better \| ### Configuration arenaType models category website inputModality image sourceModelVersion claude-opus-5 variationName public ### Reported statistics averageGenerationTimeMs 300152 battles 3892 losses 1951 standardError Not reported winRate 49.9 wins 1941 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=image-to-html) Source designarena Original model label Claude Opus 5 Source version public Observed 2026-10-21T16:37:58.959Z Evidence SHA-256 `94f97ebbdd53a8c56f138b620e59b3a9b35c66c3954dcaaa1b2ed4c71518b404` Source locator `/data/24` |  |  |  |  |  |  |  |
| [GPQA Diamond / diamond zero shot cot](https://benchize.com/benchmarks/vals-ai%3Agpqa%3Adiamond_zero_shot_cot.md) | 94.44% | SE ±1.63 pp | 3 / 40 | $0.09 | 40.59source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_gpqa.ghZZBpyU.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 94.444 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.090786 \| USD \| per_test \| Lower is better \| \| `latency` \| 40.592 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider Anthropic reasoning Not reported Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.63 pp sourcePopulation 138 stderr 1.628 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_gpqa.ghZZBpyU.json) Source Vals AI Original model label anthropic/claude-opus-5 Source version 1 Observed 2026-10-21T16:46:06.040Z Evidence SHA-256 `951eb5224097733a9d09d06c14908ae2980e2e640e539f2c284877c5092d7077` Source locator `/tasks/diamond_zero_shot_cot/anthropic~1claude-opus-5` |  |  |  |  |  |  |  |
| [DesignArena Overall frontend coding](https://benchize.com/benchmarks/designarena%3Acode.md) | 1,324elo | SE ±2.69 | 12 / 116 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=code) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1324 \| elo \| code \| Higher is better \| ### Configuration arenaType models category allcategories inputModality text sourceModelVersion claude-opus-5 variationName public ### Reported statistics Uncertainty Standard error: ±2.69 averageGenerationTimeMs 318543 battles 19278 losses 8228 standardError 2.6916 winRate 57.3 wins 11050 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=code) Source designarena Original model label Claude Opus 5 Source version public Observed 2026-10-21T16:37:57.301Z Evidence SHA-256 `0c897b58670f5e352bd123db999a40c0d1781a443964c502b90774a76a3a7758` Source locator `/data/13` |  |  |  |  |  |  |  |
| [CorpFin v2 / shared max context](https://benchize.com/benchmarks/vals-ai%3Acorp_fin_v2%3Ashared_max_context.md) | 74.94% | SE ±1.48 pp | 1 / 39 | $0.7 | 29.04source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_corp_fin_v2.CectKwl1.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 74.942 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.696945 \| USD \| per_test \| Lower is better \| \| `latency` \| 29.037 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider Anthropic reasoning Not reported Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.48 pp sourcePopulation 134 stderr 1.479 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_corp_fin_v2.CectKwl1.json) Source Vals AI Original model label anthropic/claude-opus-5 Source version 2 Observed 2026-10-21T16:45:57.998Z Evidence SHA-256 `7cf2217ab3728d5a84bffce82aab9fc52d7f810b0cbe8c65b387df47f3d31c9b` Source locator `/tasks/shared_max_context/anthropic~1claude-opus-5` |  |  |  |  |  |  |  |
| [Fortress](https://benchize.com/benchmarks/scale%3Afortress.md) | 16.84source score | CI 14.91–18.77 | 23 / 31 | — | — | [scale](https://labs.scale.com/leaderboard/fortress) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 16.84 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration claude-opus-5 sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 14.91–18.77 contaminationWarning ORS Score: 7.91 rank 20 reportedConfidenceHalfWidth 1.93 ### Source [Original source](https://labs.scale.com/leaderboard/fortress) Source scale Original model label claude-opus-5 Observed 2026-10-21T16:35:37.552Z Evidence SHA-256 `875f1c5b1112c4b84f3d17df72771ebee5c293c542cbb8ab3399e35c4f82ffa5` Source locator `/rows/19` |  |  |  |  |  |  |  |
| [Vals Multimodal Index / corp fin v2](https://benchize.com/benchmarks/vals-ai%3Avals_multimodal_index%3Acorp_fin_v2.md) | 74.94% | SE ±1.48 pp | 1 / 20 | $0.7 | 29.04source duration | [Vals AI · 1.2](https://www.vals.ai/_astro/benchmark_view_vals_multimodal_index.virVpWMs.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 74.942 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.696945 \| USD \| per_test \| Lower is better \| \| `latency` \| 29.037 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider Anthropic reasoning Not reported Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.48 pp sourcePopulation 33 stderr 1.479 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_multimodal_index.virVpWMs.json) Source Vals AI Original model label anthropic/claude-opus-5 Source version 1.2 Observed 2026-10-21T16:45:51.881Z Evidence SHA-256 `077b22575f6e075b7b78157d000ec8f94d7ead409c7dcbcf04887630ed572a2d` Source locator `/tasks/corp_fin_v2/anthropic~1claude-opus-5` |  |  |  |  |  |  |  |
| [DesignArena Website generation](https://benchize.com/benchmarks/designarena%3Awebsite.md) | 1,309elo | — | 14 / 123 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=website) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1309 \| elo \| website \| Higher is better \| ### Configuration arenaType models category website inputModality text sourceModelVersion claude-opus-5 variationName public ### Reported statistics averageGenerationTimeMs 315255 battles 10248 losses 4519 standardError Not reported winRate 55.9 wins 5729 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=website) Source designarena Original model label Claude Opus 5 Source version public Observed 2026-10-21T16:37:57.757Z Evidence SHA-256 `51873e97776a3c5ae706b24cc2c60384793dd18398df970e213a8e7c276d8ac0` Source locator `/data/16` |  |  |  |  |  |  |  |
| [DesignArena Agentic web applications](https://benchize.com/benchmarks/designarena%3Awebapps.md) | 1,266elo | SE ±8.42 | 10 / 39 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=webapps) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1266 \| elo \| webapps \| Higher is better \| ### Configuration arenaType agents category agon_webapps inputModality text sourceModelVersion claude-opus-5 variationName public ### Reported statistics Uncertainty Standard error: ±8.42 averageGenerationTimeMs Not reported battles 1916 losses 875 standardError 8.4178 winRate 54.3 wins 1041 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=webapps) Source designarena Original model label Claude Opus 5 Source version public Observed 2026-10-21T16:38:00.309Z Evidence SHA-256 `f955787274cf4ac627ada7cd33eaae2e08ef7297db92d3391340fcaa0b44a35f` Source locator `/data/11` |  |  |  |  |  |  |  |
| [DesignArena SVG generation](https://benchize.com/benchmarks/designarena%3Asvgs.md) | 1,311elo | — | 5 / 77 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=svgs) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1311 \| elo \| svgs \| Higher is better \| ### Configuration arenaType models category svg inputModality Not reported sourceModelVersion claude-opus-5 variationName public ### Reported statistics averageGenerationTimeMs 106236 battles 1704 losses 712 standardError Not reported winRate 58.2 wins 992 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=svgs) Source designarena Original model label Claude Opus 5 Source version public Observed 2026-10-21T16:38:03.249Z Evidence SHA-256 `8cbc34a474a66ef5c64f3ffe557df9b55bf7e13368c07c0214223e3ed8f3f21e` Source locator `/data/7` |  |  |  |  |  |  |  |
| [TaxEval v2 / stepwise reasoning](https://benchize.com/benchmarks/vals-ai%3Atax_eval_v2%3Astepwise_reasoning.md) | 88.31% | SE ±0.92 pp | 4 / 40 | $0.11 | 58.34source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_tax_eval_v2.B3yoffr8.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 88.307 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.114274 \| USD \| per_test \| Lower is better \| \| `latency` \| 58.339 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider Anthropic reasoning Not reported Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.92 pp sourcePopulation 145 stderr 0.919 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_eval_v2.B3yoffr8.json) Source Vals AI Original model label anthropic/claude-opus-5 Source version 2 Observed 2026-10-21T16:45:59.000Z Evidence SHA-256 `8b354a6ae848f5bb25a2e8b061b5f576d5b9e0c11b941dc1e6bed078e6529cd6` Source locator `/tasks/stepwise_reasoning/anthropic~1claude-opus-5` |  |  |  |  |  |  |  |
| [DesignArena 3D design generation](https://benchize.com/benchmarks/designarena%3A3d-design.md) | 1,335elo | — | 15 / 110 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=3d-design) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1335 \| elo \| 3d-design \| Higher is better \| ### Configuration arenaType models category 3d inputModality Not reported sourceModelVersion claude-opus-5 variationName public ### Reported statistics averageGenerationTimeMs 331090 battles 3730 losses 1504 standardError Not reported winRate 59.7 wins 2226 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=3d-design) Source designarena Original model label Claude Opus 5 Source version public Observed 2026-10-21T16:37:58.515Z Evidence SHA-256 `bcc0267f7bc7e9ec112306b3a35413cf78bbccbfaa838356232d5d5ed0b83d0f` Source locator `/data/17` |  |  |  |  |  |  |  |
| [Mystery Game Puzzles](https://benchize.com/benchmarks/epoch-ai%3Amystery_game_puzzles.md) | 37% | SE ±4.85 pp | 17 / 71 | — | — | [epoch ai · Mystery Game Puzzles](https://epoch.ai/data/benchmark_data.zip#file=mystery_game_puzzles.csv) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.37 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.37 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion Mystery Game Puzzles reasoningBudget Not reported Reasoning effort Not reported sourceModelVersion claude-opus-5 ### Reported statistics Uncertainty Standard error: ±4.85 pp standardError 0.048523658709390974 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=mystery_game_puzzles.csv) Source epoch ai Original model label claude-opus-5 Source version Mystery Game Puzzles Evaluated 2026-08-06T00:14:11.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `795b977bc82c460a5e2c1d6dd7b2569ddb21853f3829c4f6fdd16edfaf47bfcf` Source locator `/rows/99` |  |  |  |  |  |  |  |
| [Vals Multimodal Index / vibe code bench](https://benchize.com/benchmarks/vals-ai%3Avals_multimodal_index%3Avibe_code_bench.md) | 85.66% | SE ±6.08 pp | 5 / 20 | $34.09 | 3,900.6source duration | [Vals AI · 1.2](https://www.vals.ai/_astro/benchmark_view_vals_multimodal_index.virVpWMs.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 85.664 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 34.089223 \| USD \| per_test \| Lower is better \| \| `latency` \| 3900.597 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider Anthropic reasoning Not reported Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.08 pp sourcePopulation 33 stderr 6.078 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_multimodal_index.virVpWMs.json) Source Vals AI Original model label anthropic/claude-opus-5 Source version 1.2 Observed 2026-10-21T16:45:51.881Z Evidence SHA-256 `077b22575f6e075b7b78157d000ec8f94d7ead409c7dcbcf04887630ed572a2d` Source locator `/tasks/vibe_code_bench/anthropic~1claude-opus-5` |  |  |  |  |  |  |  |
| [Vending-Bench 2](https://benchize.com/benchmarks/vendingbench%3Av2.md) | — | — | — | $11,181.87 | — | [vendingbench](https://andonlabs.com/_app/immutable/chunks/Cjn0_qj9.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `final_balance` \| 11181.87333333333 \| USD \| one_simulated_year \| Higher is better \| \| `geometric_mean_balance` \| 10370.04806441597 \| USD \| positive_final_balances \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude Opus 5 thinkingEnabled Not reported ### Reported statistics confidenceHalfWidth95 4103.413783395215 positiveBalanceRuns 6 runCount 6 standardDeviation 5128.198965725353 standardError 2093.5784609159264 ### Source [Original source](https://andonlabs.com/_app/immutable/chunks/Cjn0_qj9.js) Source vendingbench Original model label Claude Opus 5 Observed 2026-10-21T16:36:40.592Z Evidence SHA-256 `1a0b043147050298c405bcb743d73e425d532464202231cd18c27f836fa5f223` Source locator `/rows/13` |  |  |  |  |  |  |  |
| [GPQA Diamond](https://benchize.com/benchmarks/gpqa-diamond.md) | 93.43% | SE ±1.24 pp | 5 / 40 | $0.1 | 39.59source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_gpqa.ghZZBpyU.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 93.434 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.095481 \| USD \| per_test \| Lower is better \| \| `latency` \| 39.588 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider Anthropic reasoning Not reported Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.24 pp sourcePopulation 138 stderr 1.244 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_gpqa.ghZZBpyU.json) Source Vals AI Original model label anthropic/claude-opus-5 Source version 1 Observed 2026-10-21T16:46:06.040Z Evidence SHA-256 `951eb5224097733a9d09d06c14908ae2980e2e640e539f2c284877c5092d7077` Source locator `/tasks/overall/anthropic~1claude-opus-5` |  |  |  |  |  |  |  |
| [TaxEval v2 / overall](https://benchize.com/benchmarks/vals-ai%3Atax_eval_v2%3Aoverall.md) | 75.14% | SE ±0.83 pp | 11 / 40 | $0.11 | 58.34source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_tax_eval_v2.B3yoffr8.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 75.143 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.114274 \| USD \| per_test \| Lower is better \| \| `latency` \| 58.339 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider Anthropic reasoning Not reported Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.83 pp sourcePopulation 145 stderr 0.832 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_eval_v2.B3yoffr8.json) Source Vals AI Original model label anthropic/claude-opus-5 Source version 2 Observed 2026-10-21T16:45:59.000Z Evidence SHA-256 `8b354a6ae848f5bb25a2e8b061b5f576d5b9e0c11b941dc1e6bed078e6529cd6` Source locator `/tasks/overall/anthropic~1claude-opus-5` |  |  |  |  |  |  |  |
| [GPQA Diamond / diamond few shot cot](https://benchize.com/benchmarks/vals-ai%3Agpqa%3Adiamond_few_shot_cot.md) | 92.42% | SE ±1.88 pp | 8 / 40 | $0.1 | 38.59source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_gpqa.ghZZBpyU.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 92.424 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.100176 \| USD \| per_test \| Lower is better \| \| `latency` \| 38.585 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider Anthropic reasoning Not reported Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.88 pp sourcePopulation 138 stderr 1.881 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_gpqa.ghZZBpyU.json) Source Vals AI Original model label anthropic/claude-opus-5 Source version 1 Observed 2026-10-21T16:46:06.040Z Evidence SHA-256 `951eb5224097733a9d09d06c14908ae2980e2e640e539f2c284877c5092d7077` Source locator `/tasks/diamond_few_shot_cot/anthropic~1claude-opus-5` |  |  |  |  |  |  |  |
| [Rapidata SVG generation — Overall preference](https://benchize.com/benchmarks/rapidata%3Asvg%3Aoverall.md) | 1,081.29elo | CI 1,070.75–1,091.83 | 11 / 37 | — | — | [rapidata · v1](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1081.2919971819406 \| elo \| overall \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion overall participantId par_1SfXO7B9TVx3E2 sourceModelVersion claude-opus-5 weighted false ### Reported statistics Uncertainty Confidence interval: 1,070.75–1,091.83 confidenceIntervalLowerOffset 10.541720117890463 confidenceIntervalUpperOffset 10.54172011789069 totalMatches 23775.249938304034 wins 13756.25250767494 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query) Source rapidata Original model label claude-opus-5 Source version v1 Observed 2026-10-21T16:37:39.078Z Evidence SHA-256 `4b73ff7e4ca0ecfd64f7888c2d64f3398a058c945c4644acd54eddb330e16d66` Source locator `/items/20` |  |  |  |  |  |  |  |
| [TaxEval v2 / correctness](https://benchize.com/benchmarks/vals-ai%3Atax_eval_v2%3Acorrectness.md) | 61.98% | SE ±1.39 pp | 20 / 40 | $0.11 | 58.34source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_tax_eval_v2.B3yoffr8.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 61.979 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.114274 \| USD \| per_test \| Lower is better \| \| `latency` \| 58.339 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider Anthropic reasoning Not reported Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.39 pp sourcePopulation 145 stderr 1.388 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_eval_v2.B3yoffr8.json) Source Vals AI Original model label anthropic/claude-opus-5 Source version 2 Observed 2026-10-21T16:45:59.000Z Evidence SHA-256 `8b354a6ae848f5bb25a2e8b061b5f576d5b9e0c11b941dc1e6bed078e6529cd6` Source locator `/tasks/correctness/anthropic~1claude-opus-5` |  |  |  |  |  |  |  |
| [GPQA Diamond](https://benchize.com/benchmarks/gpqa-diamond.md) | 92.93% | SE ±1.83 pp | 14 / 125 | — | — | [epoch ai · GPQA diamond](https://epoch.ai/data/benchmark_data.zip#file=gpqa_diamond.csv) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.9292929292929293 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.9292929292929293 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion GPQA diamond reasoningBudget Not reported Reasoning effort Not reported sourceModelVersion claude-opus-5 ### Reported statistics Uncertainty Standard error: ±1.83 pp standardError 0.018263105420199485 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=gpqa_diamond.csv) Source epoch ai Original model label claude-opus-5 Source version GPQA diamond Evaluated 2026-08-06T22:21:07.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `4b2dd8376cdd249a2c3065603575208fa726c15eabbb1622689a9abc146ba29a` Source locator `/rows/122` |  |  |  |  |  |  |  |
| [SWE-bench / >4 hours](https://benchize.com/benchmarks/vals-ai%3Aswebench%3A%3E4%20hours.md) | 100% | SE ±0 pp | 1 / 39 | $3.42 | 2,224.45source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 100 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.416648 \| USD \| per_test \| Lower is better \| \| `latency` \| 2224.447 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider Anthropic reasoning Not reported Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 88 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label anthropic/claude-opus-5 Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/>4 hours/anthropic~1claude-opus-5` |  |  |  |  |  |  |  |
| [SWE-bench / <15 min fix](https://benchize.com/benchmarks/vals-ai%3Aswebench%3A%3C15%20min%20fix.md) | 98.45% | SE ±0.89 pp | 1 / 39 | $0.88 | 410.88source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 98.454 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.881728 \| USD \| per_test \| Lower is better \| \| `latency` \| 410.881 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider Anthropic reasoning Not reported Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.89 pp sourcePopulation 88 stderr 0.888 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label anthropic/claude-opus-5 Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/<15 min fix/anthropic~1claude-opus-5` |  |  |  |  |  |  |  |
| [Judgemark v4](https://benchize.com/benchmarks/eq-bench%3Ajudgemark-v4.md) | 78.81% | CI 74.03–85.75% | 7 / 38 | — | — | [eq bench · judgemark-v4](https://eqbench.com/judgemark-v4.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.788124 \| score_fraction \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol judgemark-v4 sourceModelVersion claude-opus-5 ### Reported statistics Uncertainty Confidence interval: 74.03–85.75% confidenceIntervalHigh 0.857485 confidenceIntervalLow 0.740303 ### Source [Original source](https://eqbench.com/judgemark-v4.js) Source eq bench Original model label claude-opus-5 Source version judgemark-v4 Observed 2026-10-21T16:35:03.901Z Evidence SHA-256 `2b0d42aef4f614dd199dc38399be7b88075a919db52020c3759f190defc92a4d` Source locator `/leaderboardDataJudgemarkV4/6` |  |  |  |  |  |  |  |
| [DesignArena UI component generation](https://benchize.com/benchmarks/designarena%3Aui-components.md) | 1,349elo | — | 7 / 112 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=ui-components) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1349 \| elo \| ui-components \| Higher is better \| ### Configuration arenaType models category uicomponent inputModality Not reported sourceModelVersion claude-opus-5 variationName public ### Reported statistics averageGenerationTimeMs 222004 battles 1617 losses 634 standardError Not reported winRate 60.8 wins 983 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ui-components) Source designarena Original model label Claude Opus 5 Source version public Observed 2026-10-21T16:37:57.993Z Evidence SHA-256 `46482ec1b4012638eace65493daea4750e2088098018fd9d5fc46126fc1f8557` Source locator `/data/6` |  |  |  |  |  |  |  |

---
Cite as: Claude Opus 5 — Benchize, https://benchize.com/models/claude-opus-5 (retrieved 2026-10-21)