# Vals Index / finance agent > Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/vals-ai%3Avals_index%3Afinance_agent. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/vals-ai%3Avals_index%3Afinance_agent. A single measure of AI's potential economic impact — agentic model performance across finance, coding, legal, and tax tasks, weighted by each sector's share of U.S. GDP. Canonical URL: https://benchize.com/benchmarks/vals-ai%3Avals_index%3Afinance_agent 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. A single measure of AI's potential economic impact — agentic model performance across finance, coding, legal, and tax tasks, weighted by each sector's share of U.S. GDP. Composite indexes · Models tested: 14 · Score publishers: Vals AI ## Model results | # | Model | Score | ± | Cost | Latency | | | --- | --- | --- | --- | --- | --- | --- | | 1 | [Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-max.md)Max | 67.85% | SE ±2.05 pp | $8.91 | 1,980.12source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 67.846 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 8.908721 \| USD \| per_test \| Lower is better \| \| `latency` \| 1980.122 \| 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: ±2.05 pp sourcePopulation 23 stderr 2.051 tokenTotals {"cache_read_tokens":362746415,"cache_write_tokens":348503177,"input_tokens":711290297,"output_tokens":106934250,"reasoning_tokens":92568283} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 2.2 Observed 2026-10-21T16:45:49.430Z Evidence SHA-256 `0e95aee94cd2bf34bc4b43a8f4bb16c7817de138613c21011873fea4e0786b45` Source locator `/tasks/finance_agent/anthropic~1claude-opus-5-5` | | | | | | | | 2 | [Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High | 67.66% | SE ±2 pp | $4.32 | 793.03source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 67.658 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.315759 \| USD \| per_test \| Lower is better \| \| `latency` \| 793.03 \| 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: ±2 pp sourcePopulation 23 stderr 2 tokenTotals {"cache_read_tokens":291037965,"cache_write_tokens":null,"input_tokens":602790494,"output_tokens":31627905,"reasoning_tokens":14149611} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) Source Vals AI Original model label google/gemini-4-argon Source version 2.2 Observed 2026-10-21T16:45:49.430Z Evidence SHA-256 `0e95aee94cd2bf34bc4b43a8f4bb16c7817de138613c21011873fea4e0786b45` Source locator `/tasks/finance_agent/google~1gemini-4-argon` | | | | | | | | 3 | [Claude Sonnet 5.5](https://benchize.com/models/claude-sonnet-5-5-max.md)Max | 67.28% | SE ±2.02 pp | $6.95 | 2,066.22source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 67.275 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.950246 \| USD \| per_test \| Lower is better \| \| `latency` \| 2066.221 \| 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: ±2.02 pp sourcePopulation 23 stderr 2.023 tokenTotals {"cache_read_tokens":579490734,"cache_write_tokens":626479999,"input_tokens":1206037903,"output_tokens":148942679,"reasoning_tokens":130899975} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) Source Vals AI Original model label anthropic/claude-sonnet-5-5 Source version 2.2 Observed 2026-10-21T16:45:49.430Z Evidence SHA-256 `0e95aee94cd2bf34bc4b43a8f4bb16c7817de138613c21011873fea4e0786b45` Source locator `/tasks/finance_agent/anthropic~1claude-sonnet-5-5` | | | | | | | | 4 | [Gemini 3.8 Flash](https://benchize.com/models/gemini-3-8-flash-high.md)High | 65.76% | SE ±2.04 pp | $1.99 | 443.89source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 65.761 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.991077 \| USD \| per_test \| Lower is better \| \| `latency` \| 443.888 \| 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: ±2.04 pp sourcePopulation 23 stderr 2.039 tokenTotals {"cache_read_tokens":708933383,"cache_write_tokens":null,"input_tokens":1102307399,"output_tokens":26345690,"reasoning_tokens":18599088} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) Source Vals AI Original model label google/gemini-3.8-flash Source version 2.2 Observed 2026-10-21T16:45:49.430Z Evidence SHA-256 `0e95aee94cd2bf34bc4b43a8f4bb16c7817de138613c21011873fea4e0786b45` Source locator `/tasks/finance_agent/google~1gemini-3.8-flash` | | | | | | | | 5 | [Muse Wonder](https://benchize.com/models/muse-wonder-max.md)Max | 65.55% | SE ±2.03 pp | $2.62 | 310.13source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 65.545 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.620705 \| USD \| per_test \| Lower is better \| \| `latency` \| 310.129 \| 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: ±2.03 pp sourcePopulation 23 stderr 2.031 tokenTotals {"cache_read_tokens":190235588,"cache_write_tokens":0,"input_tokens":398379578,"output_tokens":15303665,"reasoning_tokens":9870222} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) Source Vals AI Original model label meta/muse-wonder Source version 2.2 Observed 2026-10-21T16:45:49.430Z Evidence SHA-256 `0e95aee94cd2bf34bc4b43a8f4bb16c7817de138613c21011873fea4e0786b45` Source locator `/tasks/finance_agent/meta~1muse-wonder` | | | | | | | | 6 | [Claude Haiku 5.5](https://benchize.com/models/claude-haiku-5-5-max.md)Max | 65.37% | SE ±2.06 pp | $1.64 | 1,864.63source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 65.373 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.637243 \| USD \| per_test \| Lower is better \| \| `latency` \| 1864.634 \| 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: ±2.06 pp sourcePopulation 23 stderr 2.063 tokenTotals {"cache_read_tokens":378369304,"cache_write_tokens":686667014,"input_tokens":1065081554,"output_tokens":206334140,"reasoning_tokens":194190119} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 2.2 Observed 2026-10-21T16:45:49.430Z Evidence SHA-256 `0e95aee94cd2bf34bc4b43a8f4bb16c7817de138613c21011873fea4e0786b45` Source locator `/tasks/finance_agent/anthropic~1claude-haiku-5-5` | | | | | | | | 7 | [MiMo-V2.6-Pro](https://benchize.com/models/mimo-v2-6-pro.md) | 64.26% | SE ±2.02 pp | $0.18 | 682.01source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 64.259 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.183321 \| USD \| per_test \| Lower is better \| \| `latency` \| 682.01 \| 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: ±2.02 pp sourcePopulation 23 stderr 2.015 tokenTotals {"cache_read_tokens":126914944,"cache_write_tokens":null,"input_tokens":292706558,"output_tokens":11189430,"reasoning_tokens":6591988} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) Source Vals AI Original model label xiaomi/mimo-v2.6-pro Source version 2.2 Observed 2026-10-21T16:45:49.430Z Evidence SHA-256 `0e95aee94cd2bf34bc4b43a8f4bb16c7817de138613c21011873fea4e0786b45` Source locator `/tasks/finance_agent/xiaomi~1mimo-v2.6-pro` | | | | | | | | 8 | [MiMo-V2.6-Flash](https://benchize.com/models/mimo-v2-6-flash.md) | 63.32% | SE ±2.08 pp | $0.07 | 936.35source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 63.316 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.066534 \| USD \| per_test \| Lower is better \| \| `latency` \| 936.347 \| 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: ±2.08 pp sourcePopulation 23 stderr 2.084 tokenTotals {"cache_read_tokens":208996480,"cache_write_tokens":null,"input_tokens":389007728,"output_tokens":14596133,"reasoning_tokens":8588760} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) Source Vals AI Original model label xiaomi/mimo-v2.6-flash Source version 2.2 Observed 2026-10-21T16:45:49.430Z Evidence SHA-256 `0e95aee94cd2bf34bc4b43a8f4bb16c7817de138613c21011873fea4e0786b45` Source locator `/tasks/finance_agent/xiaomi~1mimo-v2.6-flash` | | | | | | | | 9 | [DeepSeek V4.1 Flash 1017](https://benchize.com/models/deepseek-v4-1-flash-1017-max.md)Max | 62.93% | SE ±2.03 pp | $0.47 | 909.21source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 62.933 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.466261 \| USD \| per_test \| Lower is better \| \| `latency` \| 909.212 \| 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: ±2.03 pp sourcePopulation 23 stderr 2.028 tokenTotals {"cache_read_tokens":721979776,"cache_write_tokens":null,"input_tokens":1025601275,"output_tokens":94944123,"reasoning_tokens":82978352} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) Source Vals AI Original model label deepseek/deepseek-v4.1-flash-1017 Source version 2.2 Observed 2026-10-21T16:45:49.430Z Evidence SHA-256 `0e95aee94cd2bf34bc4b43a8f4bb16c7817de138613c21011873fea4e0786b45` Source locator `/tasks/finance_agent/deepseek~1deepseek-v4.1-flash-1017` | | | | | | | | 10 | [GPT-6.1 Sol](https://benchize.com/models/gpt-6-1-sol-max.md)Max | 61.82% | SE ±2.11 pp | $1.63 | 1,145.08source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 61.817 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.626543 \| USD \| per_test \| Lower is better \| \| `latency` \| 1145.078 \| 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: ±2.11 pp sourcePopulation 23 stderr 2.112 tokenTotals {"cache_read_tokens":70737183,"cache_write_tokens":182747233,"input_tokens":253535763,"output_tokens":21994277,"reasoning_tokens":16385214} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) Source Vals AI Original model label openai/gpt-6.1-sol Source version 2.2 Observed 2026-10-21T16:45:49.430Z Evidence SHA-256 `0e95aee94cd2bf34bc4b43a8f4bb16c7817de138613c21011873fea4e0786b45` Source locator `/tasks/finance_agent/openai~1gpt-6.1-sol` | | | | | | | | 11 | [GPT-6 Astra](https://benchize.com/models/gpt-6-astra-max.md)Max | 60.43% | SE ±2.12 pp | $7.82 | 1,228.75source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 60.428 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 7.823464 \| USD \| per_test \| Lower is better \| \| `latency` \| 1228.75 \| 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: ±2.12 pp sourcePopulation 23 stderr 2.12 tokenTotals {"cache_read_tokens":77618056,"cache_write_tokens":170564517,"input_tokens":248231715,"output_tokens":22170755,"reasoning_tokens":16637610} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) Source Vals AI Original model label openai/gpt-6-astra Source version 2.2 Observed 2026-10-21T16:45:49.430Z Evidence SHA-256 `0e95aee94cd2bf34bc4b43a8f4bb16c7817de138613c21011873fea4e0786b45` Source locator `/tasks/finance_agent/openai~1gpt-6-astra` | | | | | | | | 12 | [MiniMax M3.1 Flash](https://benchize.com/models/minimax-m3-1-flash-max.md)Max | 58.83% | SE ±2.07 pp | $0.16 | 904.2source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 58.826 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.158978 \| USD \| per_test \| Lower is better \| \| `latency` \| 904.204 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 262144 provider MiniMax reasoning Not reported Reasoning effort max Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.07 pp sourcePopulation 23 stderr 2.07 tokenTotals {"cache_read_tokens":234241552,"cache_write_tokens":0,"input_tokens":469331836,"output_tokens":54339785,"reasoning_tokens":45403914} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) Source Vals AI Original model label minimax/MiniMax-M3.1-flash Source version 2.2 Observed 2026-10-21T16:45:49.430Z Evidence SHA-256 `0e95aee94cd2bf34bc4b43a8f4bb16c7817de138613c21011873fea4e0786b45` Source locator `/tasks/finance_agent/minimax~1MiniMax-M3.1-flash` | | | | | | | | 13 | [DeepSeek V4 Pro 0813](https://benchize.com/models/deepseek-v4-pro-0813-max.md)Max | 57.12% | SE ±2.08 pp | $0.82 | 476.99source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 57.116 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.82234 \| USD \| per_test \| Lower is better \| \| `latency` \| 476.985 \| 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: ±2.08 pp sourcePopulation 23 stderr 2.083 tokenTotals {"cache_read_tokens":187724800,"cache_write_tokens":null,"input_tokens":380103725,"output_tokens":27027936,"reasoning_tokens":21919502} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 2.2 Observed 2026-10-21T16:45:49.430Z Evidence SHA-256 `0e95aee94cd2bf34bc4b43a8f4bb16c7817de138613c21011873fea4e0786b45` Source locator `/tasks/finance_agent/deepseek~1deepseek-v4-pro-0813` | | | | | | | | 14 | [GPT-6 Luna](https://benchize.com/models/gpt-6-luna-max.md)Max | 56.84% | SE ±2.12 pp | $0.12 | 926.86source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 56.841 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.120919 \| USD \| per_test \| Lower is better \| \| `latency` \| 926.859 \| 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: ±2.12 pp sourcePopulation 23 stderr 2.123 tokenTotals {"cache_read_tokens":189468255,"cache_write_tokens":203907655,"input_tokens":393427873,"output_tokens":45914348,"reasoning_tokens":42042763} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) Source Vals AI Original model label openai/gpt-6-luna Source version 2.2 Observed 2026-10-21T16:45:49.430Z Evidence SHA-256 `0e95aee94cd2bf34bc4b43a8f4bb16c7817de138613c21011873fea4e0786b45` Source locator `/tasks/finance_agent/openai~1gpt-6-luna` | | | | | | | --- Cite as: Vals Index / finance agent — Benchize, https://benchize.com/benchmarks/vals-ai%3Avals_index%3Afinance_agent (retrieved 2026-10-21)