# EMB / lbo > Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/vals-ai%3Aemb%3Albo. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/vals-ai%3Aemb%3Albo. Evaluating agents on Excel-based financial modeling tasks Canonical URL: https://benchize.com/benchmarks/vals-ai%3Aemb%3Albo 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. Evaluating agents on Excel-based financial modeling tasks Professional work · Models tested: 47 · Score publishers: Vals AI ## Model results | # | Model | Score | ± | Cost | Latency | | | --- | --- | --- | --- | --- | --- | --- | | 1 | [Claude Sonnet 5.5](https://benchize.com/models/claude-sonnet-5-5-max.md)Max | 69.98% | SE ±4.38 pp | $11.17 | 2,529.29source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 69.979 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 11.166488 \| USD \| per_test \| Lower is better \| \| `latency` \| 2529.291 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.38 pp sourcePopulation 76 stderr 4.376 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label anthropic/claude-sonnet-5-5 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/anthropic~1claude-sonnet-5-5` | | | | | | | | 2 | [Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max | 69.64% | SE ±4.51 pp | $18.89 | 2,121.97source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 69.64 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 18.889236 \| USD \| per_test \| Lower is better \| \| `latency` \| 2121.967 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.51 pp sourcePopulation 76 stderr 4.506 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label anthropic/claude-fable-5-1 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/anthropic~1claude-fable-5-1` | | | | | | | | 3 | [Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-max.md)Max | 69.01% | SE ±6 pp | $10.81 | 1,926.23source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 69.013 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 10.806996 \| USD \| per_test \| Lower is better \| \| `latency` \| 1926.226 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6 pp sourcePopulation 76 stderr 5.999 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/anthropic~1claude-opus-5-5` | | | | | | | | 4 | [Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High | 68.54% | SE ±4.86 pp | $21.75 | 3,392.29source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 68.543 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 21.752123 \| USD \| per_test \| Lower is better \| \| `latency` \| 3392.293 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.86 pp sourcePopulation 76 stderr 4.858 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/google~1gemini-4-argon` | | | | | | | | 5 | [GPT-5.6 Sol](https://benchize.com/models/gpt-5-6-sol-max.md)Max | 67.24% | SE ±4.87 pp | $11.1 | 725.25source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 67.242 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 11.104033 \| USD \| per_test \| Lower is better \| \| `latency` \| 725.253 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.87 pp sourcePopulation 76 stderr 4.87 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label openai/gpt-5.6-sol Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/openai~1gpt-5.6-sol` | | | | | | | | 6 | [Claude Fable 5](https://benchize.com/models/claude-fable-5-max.md)Max | 65.86% | SE ±6.47 pp | $17.46 | 2,092.83source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 65.863 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 17.455726 \| USD \| per_test \| Lower is better \| \| `latency` \| 2092.832 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.47 pp sourcePopulation 76 stderr 6.469 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label anthropic/claude-fable-5 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/anthropic~1claude-fable-5` | | | | | | | | 7 | [GPT-6.1 Sol](https://benchize.com/models/gpt-6-1-sol-max.md)Max | 64.43% | SE ±5.97 pp | $1.18 | 1,466.74source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 64.429 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.183843 \| USD \| per_test \| Lower is better \| \| `latency` \| 1466.738 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.97 pp sourcePopulation 76 stderr 5.968 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label openai/gpt-6.1-sol Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/openai~1gpt-6.1-sol` | | | | | | | | 8 | [MiMo-V2.6-Pro](https://benchize.com/models/mimo-v2-6-pro.md) | 62.35% | SE ±4.12 pp | $0.5 | 3,664.26source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 62.353 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.504393 \| USD \| per_test \| Lower is better \| \| `latency` \| 3664.258 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider Xiaomi reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.12 pp sourcePopulation 76 stderr 4.122 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label xiaomi/mimo-v2.6-pro Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/xiaomi~1mimo-v2.6-pro` | | | | | | | | 9 | [GPT-6 Astra](https://benchize.com/models/gpt-6-astra-max.md)Max | 61.83% | SE ±6.09 pp | $5.72 | 818.98source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 61.825 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 5.720048 \| USD \| per_test \| Lower is better \| \| `latency` \| 818.984 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.09 pp sourcePopulation 76 stderr 6.088 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/openai~1gpt-6-astra` | | | | | | | | 10 | [Claude Opus 5](https://benchize.com/models/claude-opus-5-max.md)Max | 61.15% | SE ±6.03 pp | $8.45 | 2,156.96source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 61.154 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 8.454608 \| USD \| per_test \| Lower is better \| \| `latency` \| 2156.964 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.03 pp sourcePopulation 76 stderr 6.027 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label anthropic/claude-opus-5 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/anthropic~1claude-opus-5` | | | | | | | | 11 | [Muse Wonder](https://benchize.com/models/muse-wonder-max.md)Max | 60.69% | SE ±6.52 pp | $9.5 | 1,638.99source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 60.69 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 9.500848 \| USD \| per_test \| Lower is better \| \| `latency` \| 1638.99 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 131072 provider Meta reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.52 pp sourcePopulation 76 stderr 6.521 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label meta/muse-wonder Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/meta~1muse-wonder` | | | | | | | | 12 | [Claude Sonnet 5](https://benchize.com/models/claude-sonnet-5-max.md)Max | 59.97% | SE ±6.15 pp | $15.35 | 4,048.24source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 59.967 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 15.354193 \| USD \| per_test \| Lower is better \| \| `latency` \| 4048.244 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.15 pp sourcePopulation 76 stderr 6.146 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label anthropic/claude-sonnet-5 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/anthropic~1claude-sonnet-5` | | | | | | | | 13 | [GPT-6 Sol](https://benchize.com/models/gpt-6-sol-max.md)Max | 59.45% | SE ±5.64 pp | $1.42 | 694.51source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 59.445 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.423011 \| USD \| per_test \| Lower is better \| \| `latency` \| 694.513 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.64 pp sourcePopulation 76 stderr 5.635 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label openai/gpt-6-sol Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/openai~1gpt-6-sol` | | | | | | | | 14 | [Gemini 3.7 Flash](https://benchize.com/models/gemini-3-7-flash-high.md)High | 59.42% | SE ±4.43 pp | $10.47 | 1,015.59source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 59.422 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 10.468715 \| USD \| per_test \| Lower is better \| \| `latency` \| 1015.586 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.43 pp sourcePopulation 76 stderr 4.427 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label google/gemini-3.7-flash Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/google~1gemini-3.7-flash` | | | | | | | | 15 | [GPT-5.6 Luna](https://benchize.com/models/gpt-5-6-luna-max.md)Max | 59.31% | SE ±5.55 pp | $0.59 | 1,052.09source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 59.306 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.592456 \| USD \| per_test \| Lower is better \| \| `latency` \| 1052.092 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.55 pp sourcePopulation 76 stderr 5.554 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label openai/gpt-5.6-luna Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/openai~1gpt-5.6-luna` | | | | | | | | 16 | [GPT-6 Luna](https://benchize.com/models/gpt-6-luna-max.md)Max | 59.1% | SE ±5.29 pp | $0.15 | 1,139.04source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 59.1 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.148123 \| USD \| per_test \| Lower is better \| \| `latency` \| 1139.036 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.29 pp sourcePopulation 76 stderr 5.289 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label openai/gpt-6-luna Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/openai~1gpt-6-luna` | | | | | | | | 17 | [Step 5 Preview](https://benchize.com/models/step-5-preview.md) | 58.93% | SE ±5.84 pp | $2.22 | 3,906.73source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 58.933 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.216785 \| USD \| per_test \| Lower is better \| \| `latency` \| 3906.731 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 1024000 provider Stepfun reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.84 pp sourcePopulation 76 stderr 5.839 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label stepfun/step-5-preview Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/stepfun~1step-5-preview` | | | | | | | | 18 | [Gemini 3.8 Flash](https://benchize.com/models/gemini-3-8-flash-high.md)High | 58.56% | SE ±6.15 pp | $13.51 | 1,125.23source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 58.56 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 13.510599 \| USD \| per_test \| Lower is better \| \| `latency` \| 1125.234 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.15 pp sourcePopulation 76 stderr 6.149 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label google/gemini-3.8-flash Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/google~1gemini-3.8-flash` | | | | | | | | 19 | [DeepSeek V4.1 Flash 1017](https://benchize.com/models/deepseek-v4-1-flash-1017-max.md)Max | 57.76% | SE ±6.01 pp | $0.47 | 1,355.48source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 57.763 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.469175 \| USD \| per_test \| Lower is better \| \| `latency` \| 1355.484 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature 1 topP 1 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.01 pp sourcePopulation 76 stderr 6.008 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label deepseek/deepseek-v4.1-flash-1017 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/deepseek~1deepseek-v4.1-flash-1017` | | | | | | | | 20 | [MiMo-V2.6-Flash](https://benchize.com/models/mimo-v2-6-flash.md) | 56.93% | SE ±5.35 pp | $0.18 | 2,303.33source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 56.926 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.177028 \| USD \| per_test \| Lower is better \| \| `latency` \| 2303.334 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider Xiaomi reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.35 pp sourcePopulation 76 stderr 5.354 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label xiaomi/mimo-v2.6-flash Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/xiaomi~1mimo-v2.6-flash` | | | | | | | | 21 | [Muse Spark 1.3](https://benchize.com/models/muse-spark-1-3-xhigh.md)Extra high | 56.58% | SE ±5.45 pp | $6.83 | 2,351.58source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 56.579 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.826336 \| USD \| per_test \| Lower is better \| \| `latency` \| 2351.579 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 131072 provider Meta reasoning Not reported Reasoning effort xhigh Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.45 pp sourcePopulation 76 stderr 5.451 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label meta/muse_spark_1_3 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/meta~1muse_spark_1_3` | | | | | | | | 22 | [Claude Opus 4.7](https://benchize.com/models/claude-opus-4-7-max.md)Max | 56.45% | SE ±6.04 pp | $17.93 | 3,015.63source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 56.449 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 17.932197 \| USD \| per_test \| Lower is better \| \| `latency` \| 3015.626 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.04 pp sourcePopulation 76 stderr 6.037 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label anthropic/claude-opus-4-7 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/anthropic~1claude-opus-4-7` | | | | | | | | 23 | [Claude Opus 4.8](https://benchize.com/models/claude-opus-4-8-max.md)Max | 54.38% | SE ±5.35 pp | $17.13 | 3,411.87source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 54.384 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 17.127734 \| USD \| per_test \| Lower is better \| \| `latency` \| 3411.868 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.35 pp sourcePopulation 76 stderr 5.352 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label anthropic/claude-opus-4-8 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/anthropic~1claude-opus-4-8` | | | | | | | | 24 | [DeepSeek V4.1 Flash](https://benchize.com/models/deepseek-v4-1-flash-high.md)High | 54.18% | SE ±5.29 pp | $0.34 | 1,116.96source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 54.183 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.338915 \| USD \| per_test \| Lower is better \| \| `latency` \| 1116.958 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.29 pp sourcePopulation 76 stderr 5.292 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label deepseek/deepseek-v4.1-flash Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/deepseek~1deepseek-v4.1-flash` | | | | | | | | 25 | [GPT-5.5](https://benchize.com/models/gpt-5-5-xhigh.md)Extra high | 53.22% | SE ±5.14 pp | $3.55 | 1,094.17source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 53.222 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.548798 \| USD \| per_test \| Lower is better \| \| `latency` \| 1094.17 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.14 pp sourcePopulation 76 stderr 5.136 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/openai~1gpt-5.5` | | | | | | | | 26 | [Claude Sonnet 4.6](https://benchize.com/models/claude-sonnet-4-6-max.md)Max | 52.54% | SE ±5.43 pp | $11.22 | 4,347.37source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 52.536 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 11.216346 \| USD \| per_test \| Lower is better \| \| `latency` \| 4347.368 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning true Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.43 pp sourcePopulation 76 stderr 5.427 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label anthropic/claude-sonnet-4-6 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/anthropic~1claude-sonnet-4-6` | | | | | | | | 27 | [Gemini 3.6 Flash](https://benchize.com/models/gemini-3-6-flash-high.md)High | 52.47% | SE ±5.34 pp | $6.34 | 1,173.46source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 52.472 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.338788 \| USD \| per_test \| Lower is better \| \| `latency` \| 1173.459 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.34 pp sourcePopulation 76 stderr 5.339 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/google~1gemini-3.6-flash` | | | | | | | | 28 | [Muse Spark Open](https://benchize.com/models/muse-spark-open-xhigh.md)Extra high | 50.7% | SE ±5.14 pp | $7.43 | 5,821.1source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 50.698 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 7.431962 \| USD \| per_test \| Lower is better \| \| `latency` \| 5821.099 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 131072 provider Together AI reasoning Not reported Reasoning effort xhigh Temperature 1 topP 1 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.14 pp sourcePopulation 76 stderr 5.141 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label meta/muse-spark-open Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/meta~1muse-spark-open` | | | | | | | | 29 | [GPT-5.6 Terra](https://benchize.com/models/gpt-5-6-terra-max.md)Max | 50.43% | SE ±6.18 pp | $2.79 | 924.29source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 50.428 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.789723 \| USD \| per_test \| Lower is better \| \| `latency` \| 924.286 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.18 pp sourcePopulation 76 stderr 6.178 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label openai/gpt-5.6-terra Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/openai~1gpt-5.6-terra` | | | | | | | | 30 | [DeepSeek V4 Pro 0813](https://benchize.com/models/deepseek-v4-pro-0813-max.md)Max | 50.29% | SE ±6.11 pp | $1.92 | 3,745.66source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 50.294 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.922378 \| USD \| per_test \| Lower is better \| \| `latency` \| 3745.657 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.11 pp sourcePopulation 76 stderr 6.108 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/deepseek~1deepseek-v4-pro-0813` | | | | | | | | 31 | [Muse Spark 1.1](https://benchize.com/models/muse-spark-1-1-xhigh.md)Extra high | 49.77% | SE ±5.37 pp | $1.74 | 1,292.91source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 49.767 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.737996 \| USD \| per_test \| Lower is better \| \| `latency` \| 1292.905 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 256000 provider Meta reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.37 pp sourcePopulation 76 stderr 5.366 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label meta/muse_spark_1_1 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/meta~1muse_spark_1_1` | | | | | | | | 32 | [MiMo-V2.5-Pro](https://benchize.com/models/mimo-v2-5-pro.md) | 47.74% | SE ±5.12 pp | $0.23 | 2,198.08source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 47.739 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.234191 \| USD \| per_test \| Lower is better \| \| `latency` \| 2198.075 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider Xiaomi reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.12 pp sourcePopulation 76 stderr 5.122 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label xiaomi/mimo-v2.5-pro Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/xiaomi~1mimo-v2.5-pro` | | | | | | | | 33 | [DeepSeek V4 Flash 0731](https://benchize.com/models/deepseek-v4-flash-0731-high.md)High | 46.48% | SE ±6.14 pp | $0.6 | 2,285.28source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 46.475 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.604921 \| USD \| per_test \| Lower is better \| \| `latency` \| 2285.283 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.14 pp sourcePopulation 76 stderr 6.136 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label deepseek/deepseek-v4-flash-0731 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/deepseek~1deepseek-v4-flash-0731` | | | | | | | | 34 | [Gemini 3.5 Flash](https://benchize.com/models/gemini-3-5-flash-high.md)High | 46.47% | SE ±5.6 pp | $6.81 | 1,383.42source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 46.47 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.810486 \| USD \| per_test \| Lower is better \| \| `latency` \| 1383.424 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.6 pp sourcePopulation 76 stderr 5.599 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label google/gemini-3.5-flash Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/google~1gemini-3.5-flash` | | | | | | | | 35 | [Muse Spark 1.2](https://benchize.com/models/muse-spark-1-2-xhigh.md)Extra high | 45.77% | SE ±5.59 pp | $2.42 | 1,213.26source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 45.765 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.418215 \| USD \| per_test \| Lower is better \| \| `latency` \| 1213.262 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 131072 provider Meta reasoning Not reported Reasoning effort xhigh Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.59 pp sourcePopulation 76 stderr 5.589 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label meta/muse_spark_1_2 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/meta~1muse_spark_1_2` | | | | | | | | 36 | [MiMo-V2.5](https://benchize.com/models/mimo-v2-5.md) | 45.05% | SE ±5.1 pp | $0.1 | 2,502.24source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 45.047 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.102455 \| USD \| per_test \| Lower is better \| \| `latency` \| 2502.244 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider Xiaomi reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.1 pp sourcePopulation 76 stderr 5.096 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label xiaomi/mimo-v2.5 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/xiaomi~1mimo-v2.5` | | | | | | | | 37 | [MiniMax M3](https://benchize.com/models/minimax-m3.md) | 44.93% | SE ±5.7 pp | $3.03 | 2,429.63source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 44.93 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.032953 \| USD \| per_test \| Lower is better \| \| `latency` \| 2429.627 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.7 pp sourcePopulation 76 stderr 5.701 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/minimax~1MiniMax-M3` | | | | | | | | 38 | [DeepSeek V4 Pro](https://benchize.com/models/deepseek-v4-pro-max.md)Max | 43.94% | SE ±3.92 pp | $0.89 | 1,042.97source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 43.938 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.886335 \| USD \| per_test \| Lower is better \| \| `latency` \| 1042.97 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.92 pp sourcePopulation 76 stderr 3.924 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label deepseek/deepseek-v4-pro Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/deepseek~1deepseek-v4-pro` | | | | | | | | 39 | [Gemini 3.5 Flash-Lite](https://benchize.com/models/gemini-3-5-flash-lite-high.md)High | 40.13% | SE ±4.73 pp | $1.24 | 536.96source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 40.127 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.241351 \| USD \| per_test \| Lower is better \| \| `latency` \| 536.961 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.73 pp sourcePopulation 76 stderr 4.732 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label google/gemini-3.5-flash-lite Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/google~1gemini-3.5-flash-lite` | | | | | | | | 40 | [Gemini 3.1 Pro Preview](https://benchize.com/models/gemini-3-1-pro-preview-high.md)High | 37.97% | SE ±4.01 pp | $4.76 | 784.35source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 37.967 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.762336 \| USD \| per_test \| Lower is better \| \| `latency` \| 784.347 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.01 pp sourcePopulation 76 stderr 4.006 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label google/gemini-3.1-pro-preview Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/google~1gemini-3.1-pro-preview` | | | | | | | | 41 | [Claude Haiku 5.5](https://benchize.com/models/claude-haiku-5-5-max.md)Max | 28.16% | SE ±9.61 pp | $0.79 | 911.52source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 28.155 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.785699 \| USD \| per_test \| Lower is better \| \| `latency` \| 911.522 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±9.61 pp sourcePopulation 76 stderr 9.61 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/anthropic~1claude-haiku-5-5` | | | | | | | | 42 | [MiniMax M2.7](https://benchize.com/models/minimax-m2-7.md) | 25.78% | SE ±4.08 pp | $2.69 | 1,815.77source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 25.782 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.692152 \| USD \| per_test \| Lower is better \| \| `latency` \| 1815.768 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 80000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.08 pp sourcePopulation 76 stderr 4.076 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label minimax/MiniMax-M2.7 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/minimax~1MiniMax-M2.7` | | | | | | | | 43 | [Nemotron 3 Ultra](https://benchize.com/models/nemotron-3-ultra-550b-a55b.md) | 23.3% | SE ±4.7 pp | — | 3,813.92source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 23.302 \| percent \| reported \| Higher is better \| \| `latency` \| 3813.919 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider Nvidia reasoning Not reported Reasoning effort unknown Temperature Not reported topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.7 pp sourcePopulation 76 stderr 4.695 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label nvidia/nemotron-3-ultra-550b-a55b Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/nvidia~1nemotron-3-ultra-550b-a55b` | | | | | | | | 44 | [Mistral Medium 3.5](https://benchize.com/models/mistral-medium-3-5-high.md)High | 9.61% | SE ±3.15 pp | $13.14 | 3,864.56source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 9.61 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 13.135423 \| USD \| per_test \| Lower is better \| \| `latency` \| 3864.563 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 80000 provider Mistral AI reasoning Not reported Reasoning effort high Temperature 0.7 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.15 pp sourcePopulation 76 stderr 3.145 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label mistralai/mistral-medium-3.5 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/mistralai~1mistral-medium-3.5` | | | | | | | | 45 | [Gemini 3.1 Flash Lite Preview](https://benchize.com/models/gemini-3-1-flash-lite-preview-high.md)High | 8.81% | SE ±2.18 pp | $0.04 | 49.22source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 8.805 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.037241 \| USD \| per_test \| Lower is better \| \| `latency` \| 49.222 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.18 pp sourcePopulation 76 stderr 2.184 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label google/gemini-3.1-flash-lite-preview Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/google~1gemini-3.1-flash-lite-preview` | | | | | | | | 46 | [Mercury 2.5](https://benchize.com/models/mercury-2-5-high.md)High | 8.25% | SE ±2.82 pp | $0.38 | 259.93source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 8.25 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.375911 \| USD \| per_test \| Lower is better \| \| `latency` \| 259.925 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Inception reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.82 pp sourcePopulation 76 stderr 2.824 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label inception/mercury-2.5 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/inception~1mercury-2.5` | | | | | | | | 47 | [Gemini 3 Flash Preview](https://benchize.com/models/gemini-3-flash-preview-high.md)High | 7.54% | SE ±3.32 pp | $0.34 | 292.99source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 7.54 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.338627 \| USD \| per_test \| Lower is better \| \| `latency` \| 292.987 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.32 pp sourcePopulation 76 stderr 3.319 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label google/gemini-3-flash-preview Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/google~1gemini-3-flash-preview` | | | | | | | --- Cite as: EMB / lbo — Benchize, https://benchize.com/benchmarks/vals-ai%3Aemb%3Albo (retrieved 2026-10-21)