GDPval Extended — Mercor evaluation (GDPval Extended (Mercor))

We show this table for reference; we do not rank on it.

Producing workplace deliverables from reference files. This table shows Mercor-run configurations for reference and is excluded from model rankings.

Evaluation results published by Mercor. Published evaluation aggregates only; task contents and dataset license grants are not included.

Mean Score on GDPval Extended (Mercor) — October 15, 2026 capture

We mirror the published mean score view for GDPval Extended (Mercor). Opus 5.5 leads the public snapshot at 75.80%, followed by Sonnet 5.5 (70.90%) and Fable 5.1 (68.70%). We do not use these results to rank models overall.

Opus 5.5

Anthropic

Mercor extended-set run · max reasoning

Published margin ±3 · Original set 88.3% ±1.5 · 516 reported samples

75.80%

Sonnet 5.5

Anthropic

Mercor extended-set run · max reasoning

Published margin ±3.3 · Original set 86.5% ±1.7 · 505 reported samples

70.90%

Fable 5.1

Anthropic

Mercor extended-set run · max reasoning

Published margin ±3.1 · Original set 86.6% ±1.7 · 528 reported samples

68.70%

42 configurationsAgenticDated Mercor configurationsDisplay onlyUpdated October 15, 2026 capture

Mean Score table (42 configurations)

Mean Score results for GDPval Extended (Mercor)
Rank	Model / configuration	Score	Parameters (B)	Open / closed
1	Opus 5.5AnthropicMercor extended-set run · max reasoningPublished margin ±3 · Original set 88.3% ±1.5 · 516 reported samples	75.80%	Not reported	Unknown
2	Sonnet 5.5AnthropicMercor extended-set run · max reasoningPublished margin ±3.3 · Original set 86.5% ±1.7 · 505 reported samples	70.90%	Not reported	Unknown
3	Fable 5.1AnthropicMercor extended-set run · max reasoningPublished margin ±3.1 · Original set 86.6% ±1.7 · 528 reported samples	68.70%	Not reported	Unknown
4	Haiku 5.5AnthropicMercor extended-set run · max reasoningPublished margin ±3.1 · Original set 85.5% ±1.6 · 506 reported samples	66.00%	Not reported	Unknown
5	Fable 5AnthropicMercor extended-set run · max reasoningPublished margin ±2.9 · Original set 78.6% ±5.1 · 521 reported samples	65.30%	Not reported	Unknown
6	GPT-6 AstraOpenAIMercor extended-set run · max reasoningPublished margin ±3.1 · Original set 86.7% ±1.7 · 528 reported samples	64.10%	Not reported	Unknown
7	Opus 5AnthropicMercor extended-set run · max reasoningPublished margin ±3.3 · Original set 85.6% ±1.9 · 527 reported samples	62.90%	Not reported	Unknown
8	Grok 4.6xAIMercor extended-set run · xhigh reasoningPublished margin ±2.9 · Original set 86% ±1.6 · 526 reported samples	61.80%	Not reported	Unknown
9	Fable 5.1AnthropicMercor extended-set run · high reasoningPublished margin ±4 · Original set 81.4% ±2.7 · 528 reported samples	61.50%	Not reported	Unknown
10	Gemini 3.8 FlashGoogleMercor extended-set run · high reasoningPublished margin ±3.1 · Original set 83.5% ±1.6 · 528 reported samples	60.40%	Not reported	Unknown
11	Opus 4.8AnthropicMercor extended-set run · max reasoningPublished margin ±2.9 · Original set 84.5% ±1.7 · 528 reported samples	58.90%	Not reported	Unknown
12	GPT-6 SolOpenAIMercor extended-set run · max reasoningPublished margin ±3.1 · Original set 83.5% ±1.9 · 528 reported samples	58.70%	Not reported	Unknown
13	DeepSeek-V4.1-FlashDeepSeekMercor extended-set run · max reasoningPublished margin ±3 · Original set 86.7% ±1.5 · 478 reported samples	58.60%	Not reported	Unknown
14	Gemini 3.7 FlashGoogleMercor extended-set run · high reasoningPublished margin ±2.9 · Original set 85.2% ±1.7 · 528 reported samples	57.80%	Not reported	Unknown
15	Muse Spark 1.2MetaMercor extended-set run · xhigh reasoningPublished margin ±3.2 · Original set 83.8% ±2 · 524 reported samples	57.50%	Not reported	Unknown
16	Kimi K3KimiMercor extended-set run · max reasoningPublished margin ±3.2 · Original set 78.8% ±5.1 · 526 reported samples	56.40%	Not reported	Unknown
17	Muse Spark 1.3MetaMercor extended-set run · max reasoningPublished margin ±3.5 · Original set not reported · 527 reported samples	55.90%	Not reported	Unknown
18	GPT-5.5OpenAIMercor extended-set run · xhigh reasoningPublished margin ±2.6 · Original set 79.9% ±5.2 · 528 reported samples	54.50%	Not reported	Unknown
19	Sonnet 5AnthropicMercor extended-set run · max reasoningPublished margin ±3 · Original set 77.6% ±5.2 · 528 reported samples	54.20%	Not reported	Unknown
20	Opus 4.7AnthropicMercor extended-set run · max reasoningPublished margin ±2.7 · Original set 79.8% ±5.1 · 528 reported samples	53.80%	Not reported	Unknown
21	Opus 4.6AnthropicMercor extended-set run · max reasoningPublished margin ±2.8 · Original set not reported · 528 reported samples	53.00%	Not reported	Unknown
22	Muse Spark 1.1MetaMercor extended-set run · xhigh reasoningPublished margin ±3.1 · Original set 82.4% ±2 · 522 reported samples	52.40%	Not reported	Unknown
23	Gemini 3.6 FlashGoogleMercor extended-set run · high reasoningPublished margin ±2.9 · Original set 83.8% ±1.7 · 527 reported samples	52.20%	Not reported	Unknown
24	GPT-5.6 Sol (Pro)OpenAIMercor extended-set run · max reasoningPublished margin ±3.1 · Original set 75.6% ±5.3 · 528 reported samples	52.00%	Not reported	Unknown
25	Qwen3.8-MaxAlibabaMercor extended-set run · xhigh reasoningPublished margin ±3.5 · Original set 83.3% ±2 · 528 reported samples	51.10%	Not reported	Unknown
26	Sonnet 4.6AnthropicMercor extended-set run · high reasoningPublished margin ±2.8 · Original set 79% ±5.2 · 528 reported samples	51.00%	Not reported	Unknown
27	Grok 4.5xAIMercor extended-set run · high reasoningPublished margin ±3.3 · Original set 78.8% ±5.2 · 528 reported samples	51.00%	Not reported	Unknown
28	GPT-6 LunaOpenAIMercor extended-set run · max reasoningPublished margin ±2.9 · Original set 80.1% ±2.2 · 527 reported samples	48.90%	Not reported	Unknown
29	GPT-5.4OpenAIMercor extended-set run · xhigh reasoningPublished margin ±2.7 · Original set 60% ±5.7 · 528 reported samples	48.00%	Not reported	Unknown
30	GLM-5.2ZhipuMercor extended-set run · max reasoningPublished margin ±3 · Original set 78.2% ±5.2 · 529 reported samples	47.30%	Not reported	Unknown
31	GPT-5.6 TerraOpenAIMercor extended-set run · max reasoningPublished margin ±3 · Original set 77.1% ±5.2 · 528 reported samples	47.20%	Not reported	Unknown
32	GPT-5.6 LunaOpenAIMercor extended-set run · max reasoningPublished margin ±3 · Original set 72.5% ±5.5 · 528 reported samples	44.90%	Not reported	Unknown
33	DeepSeek-V4-ProDeepSeekMercor extended-set run · max reasoningPublished margin ±3.1 · Original set 74.3% ±5.1 · 528 reported samples	42.00%	Not reported	Unknown
34	Gemini 3.1 ProGoogleMercor extended-set run · high reasoningPublished margin ±2.7 · Original set 68.5% ±5.5 · 527 reported samples	41.90%	Not reported	Unknown
35	Kimi K2.7 CodeKimiMercor extended-set run · high reasoningPublished margin ±2.8 · Original set 70.1% ±5.4 · 528 reported samples	41.00%	Not reported	Unknown
36	InklingThinking MachinesMercor extended-set run · high reasoningPublished margin ±2.8 · Original set 65.4% ±5.6 · 528 reported samples	39.50%	Not reported	Unknown
37	MiniMax-M3MiniMaxMercor extended-set run · high reasoningPublished margin ±2.9 · Original set 74.8% ±5.3 · 528 reported samples	38.80%	Not reported	Unknown
38	Nemotron 3 UltraNVIDIAMercor extended-set run · high reasoningPublished margin ±2.6 · Original set 63.5% ±3.1 · 528 reported samples	38.20%	Not reported	Unknown
39	Qwen3.5AlibabaMercor extended-set runPublished margin ±2.9 · Original set 71% ±2.2 · 528 reported samples	35.40%	Not reported	Unknown
40	MiniMax-M2.7MiniMaxMercor extended-set run · high reasoningPublished margin ±2.5 · Original set 68.3% ±5.3 · 528 reported samples	32.40%	Not reported	Unknown
41	Gemini 3.5 FlashGoogleMercor extended-set run · high reasoningPublished margin ±4.4 · Original set 72.4% ±5.2 · 527 reported samples	31.60%	Not reported	Unknown
42	Kimi K2 (Thinking)KimiMercor extended-set run · high reasoningPublished margin ±2.5 · Original set 54.1% ±5.6 · 528 reported samples	26.00%	Not reported	Unknown

How to read this Mercor evaluation

We captured Mercor's GDPval Extended results on October 15, 2026. The table preserves 42 published configurations, their source identifiers, reasoning settings, and disclosed mean score values. These are results from Mercor's evaluation setup; we did not rerun them.

The headline uses the 132 Mercor-built tasks. The paired original-set values refer to the separately listed 213-task public benchmark. Missing baselines remain unreported. We keep the extension and original set separate from their upstream benchmark-owner and provider-run tables.

The headline is the published mean score, which can include partial credit. It must not be read as a strict task-completion rate.

The row labels retain published error margins and sample counts when supplied. Missing margins and counts remain unreported; a sample count is not used to reconstruct a task denominator. Except where the dedicated source defines an interval, the confidence level is unreported. Equal displayed scores and overlapping margins do not establish statistical ties. Capture time does not establish individual evaluation dates.

The general methodology lists llm-as-a-judge (lmaaj) and a judge of Gemini 3 Flash Preview. Its run-count label is k = 4. Those notes describe the original public benchmark; extension-specific changes are not established by that reference.

Snapshot

Mean Score42 configurationsMercor task extensionDisplay only

Mercor GDPval Extended results Mercor APEX benchmark index Mercor methodology Paired Mercor original-set results Source paper Upstream dataset

The published GDPval Extended (Mercor) snapshot places Opus 5.5 first at 75.80%. The third row is 7.10 points behind. The broader top-10 range is 15.40 points, so the table still separates the published systems.

42 configurations are shown for GDPval Extended (Mercor). The benchmark falls in the Agentic category. We keep external benchmark mirrors separate from the weighted global scoring system, so these results remain source-specific evidence. GDPval Extended (Mercor) is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About GDPval Extended (Mercor)

Tasks

132 Mercor tasks; 213 tasks in the separately reported original set

Format

Mean Score

Difficulty

Source-specific evaluation

The selected headline is Mean Score. Source model identifiers, effort settings, published margins, and reported sample counts remain attached to the source configuration. Public-set results and Mercor task extensions occupy separate tables.

GDPval Extended evaluation results Public benchmark source

Freshness and provenance

Version

GDPval Extended; Mercor Mean Score

Refresh cadence

Reviewed dated source capture

Staleness state

Dated Mercor configurations

Question availability

Upstream task access and terms; only aggregate results mirrored

Dated Mercor configurationsDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

Questions

What does GDPval Extended (Mercor) measure?

Producing workplace deliverables from reference files. This table shows Mercor-run configurations for reference and is excluded from model rankings.

Which model leads the published GDPval Extended (Mercor) snapshot?

Opus 5.5 currently leads the published GDPval Extended (Mercor) snapshot with 75.80% mean score. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on GDPval Extended (Mercor)?

The October 15, 2026 capture snapshot contains 42 source configurations.

Last updated: October 15, 2026 capture · mirrored from the public benchmark leaderboard

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 5,600+ readers.

One email each week. Unsubscribe anytime.