# MMMU-Pro Extended — Mercor evaluation (MMMU-Pro Extended (Mercor))

> Answering questions that require both visual and textual understanding. This table shows Mercor-run configurations for reference and is excluded from model rankings.

Canonical page: https://benchlm.ai/benchmarks/mercormmmuproextended

- Category: [Multimodal & Grounded](/multimodal-grounded)
- Last updated: October 15, 2026 capture

Evaluation results published by [Mercor](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/). Published evaluation aggregates only; task contents and dataset license grants are not included.

We captured Mercor's MMMU-Pro Extended results on October 15, 2026. The table preserves 38 published configurations, their source identifiers, reasoning settings, and disclosed pass@1 values. These are results from Mercor's evaluation setup; we did not rerun them.

The headline uses the 140 Mercor-built tasks. The paired original-set values refer to the separately listed 1730-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 source page's selected Pass@1 metric. The task set, harness, tools, and grader belong to this Mercor run and may differ from another evaluator's results.

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 programmatic multiple-choice answer extraction and a judge of None. Its run-count label is k = 3. Those notes describe the original public benchmark; extension-specific changes are not established by that reference.

- [Mercor MMMU-Pro Extended results](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/)
- [Mercor APEX benchmark index](https://www.mercor.com/apex/)
- [Mercor methodology](https://www.mercor.com/apex/methodology/)
- [Paired Mercor original-set results](https://www.mercor.com/apex/oss-benchmarks/oss-mmmu-pro-leaderboard/)
- [Source paper](https://arxiv.org/abs/2409.02813)
- [Upstream evaluation code](https://github.com/MMMU-Benchmark/MMMU)
- [Upstream dataset](https://huggingface.co/datasets/MMMU/MMMU_Pro)

## About MMMU-Pro Extended (Mercor)

- Tasks: 140 Mercor tasks; 1730 tasks in the separately reported original set
- Format: Pass@1
- Difficulty: Source-specific evaluation
- Paper: [MMMU-Pro Extended evaluation results](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/)

The selected headline is Pass@1. 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.

MMMU-Pro Extended (Mercor) is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (38 configurations)

| Rank | Model | Configuration | Creator | Score |
|------|-------|---------------|---------|-------|
| 1 | [GPT-6.1 Sol](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · max reasoning · Published margin ±7.6 · Original set 85.8% ±1.6 · 408 reported samples | OpenAI | 61.30% |
| 2 | [GPT-6 Astra](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · max reasoning · Published margin ±7.5 · Original set 87.5% ±1.5 · 419 reported samples | OpenAI | 60.00% |
| 3 | [GPT-5.6 Sol (Pro)](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · max reasoning · Published margin ±7.5 · Original set not reported · 419 reported samples | OpenAI | 51.90% |
| 4 | [GPT-6 Sol](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · max reasoning · Published margin ±7.6 · Original set 83% ±1.7 · 420 reported samples | OpenAI | 51.90% |
| 5 | [Opus 5.5](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · max reasoning · Published margin ±7.6 · Original set 87.4% ±1.5 · 419 reported samples | Anthropic | 51.00% |
| 6 | [Fable 5.1](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · max reasoning · Published margin ±7.4 · Original set 86.1% ±1.6 · 420 reported samples | Anthropic | 47.60% |
| 7 | [GPT-5.6 Terra](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · max reasoning · Published margin ±7.6 · Original set 80.9% ±1.7 · 420 reported samples | OpenAI | 47.40% |
| 8 | [Sonnet 5.5](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · max reasoning · Published margin ±7.8 · Original set 85.8% ±1.6 · 393 reported samples | Anthropic | 44.40% |
| 9 | [GPT-5.5](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · xhigh reasoning · Published margin ±7.4 · Original set 81.8% ±1.7 · 420 reported samples | OpenAI | 43.80% |
| 10 | [GPT-5.4](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · xhigh reasoning · Published margin ±6.9 · Original set 80.8% ±1.7 · 420 reported samples | OpenAI | 39.80% |
| 11 | [GPT-5.6 Luna](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · max reasoning · Published margin ±7 · Original set 79.1% ±1.8 · 416 reported samples | OpenAI | 39.20% |
| 12 | [Fable 5](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · max reasoning · Published margin ±7.1 · Original set 72.7% ±2.1 · 420 reported samples | Anthropic | 37.60% |
| 13 | [Gemini 3.7 Flash](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · high reasoning · Published margin ±6.5 · Original set 85.2% ±1.6 · 420 reported samples | Google | 36.40% |
| 14 | [Gemini 3.8 Flash](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · high reasoning · Published margin ±6.7 · Original set 85.3% ±1.6 · 420 reported samples | Google | 36.40% |
| 15 | [Kimi K3](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · max reasoning · Published margin ±6.4 · Original set 80.7% ±1.7 · 420 reported samples | Kimi | 36.00% |
| 16 | [Muse Spark 1.1](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · xhigh reasoning · Published margin ±6.6 · Original set 81.3% ±1.7 · 410 reported samples | Meta | 35.50% |
| 17 | [Qwen3.8-Max](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · xhigh reasoning · Published margin ±6.8 · Original set 82.8% ±1.7 · 420 reported samples | Alibaba | 34.80% |
| 18 | [GPT-6 Luna](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · max reasoning · Published margin ±6.8 · Original set 76.6% ±1.9 · 420 reported samples | OpenAI | 34.80% |
| 19 | [Opus 5](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · high reasoning · Published margin ±7 · Original set not reported · 420 reported samples | Anthropic | 34.30% |
| 20 | [Fable 5](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · high reasoning · Published margin ±6.8 · Original set not reported · 420 reported samples | Anthropic | 34.30% |
| 21 | [Muse Spark 1.3](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · xhigh reasoning · Published margin ±6.5 · Original set 81.8% ±1.7 · 420 reported samples | Meta | 33.80% |
| 22 | [Haiku 5.5](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · max reasoning · Published margin ±6.2 · Original set 79.1% ±1.8 · 420 reported samples | Anthropic | 31.90% |
| 23 | [Opus 4.8](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · high reasoning · Published margin ±6.5 · Original set not reported · 420 reported samples | Anthropic | 31.40% |
| 24 | [Gemini 3.1 Pro](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · high reasoning · Published margin ±6.4 · Original set 84.3% ±1.6 · 420 reported samples | Google | 31.00% |
| 25 | [Muse Spark 1.2](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · xhigh reasoning · Published margin ±6.2 · Original set 81.4% ±1.7 · 420 reported samples | Meta | 30.20% |
| 26 | [Grok 4.5](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · high reasoning · Published margin ±6.3 · Original set 79% ±1.8 · 420 reported samples | xAI | 29.80% |
| 27 | [Gemini 3.6 Flash](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · high reasoning · Published margin ±6 · Original set 83.7% ±1.7 · 420 reported samples | Google | 29.00% |
| 28 | [Gemini 3.5 Flash](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · high reasoning · Published margin ±6.3 · Original set 84.7% ±1.6 · 419 reported samples | Google | 28.80% |
| 29 | [Opus 4.7](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · high reasoning · Published margin ±6.4 · Original set 78.6% ±1.8 · 420 reported samples | Anthropic | 28.30% |
| 30 | [Grok 4.6](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · xhigh reasoning · Published margin ±6.2 · Original set 80.5% ±1.8 · 420 reported samples | xAI | 26.00% |
| 31 | [DeepSeek-V4.1-Flash](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · max reasoning · Published margin ±5.7 · Original set 76.6% ±1.9 · 420 reported samples | DeepSeek | 25.00% |
| 32 | [Qwen3.5](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · Published margin ±5.4 · Original set not reported · 420 reported samples | Alibaba | 24.30% |
| 33 | [Inkling](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · high reasoning · Published margin ±5.8 · Original set 69.7% ±2 · 420 reported samples | Thinking Machines | 24.00% |
| 34 | [Kimi K2.7 Code](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · high reasoning · Published margin ±5.5 · Original set not reported · 420 reported samples | Kimi | 23.10% |
| 35 | [GLM-5.3-Flash](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · max reasoning · Published margin ±5.2 · Original set 78.4% ±1.8 · 420 reported samples | Zhipu | 22.60% |
| 36 | [Sonnet 5](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · high reasoning · Published margin ±5.4 · Original set not reported · 420 reported samples | Anthropic | 20.70% |
| 37 | [Sonnet 4.6](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · high reasoning · Published margin ±5.5 · Original set 74.6% ±2 · 424 reported samples | Anthropic | 19.90% |
| 38 | [MiniMax-M3](https://www.mercor.com/apex/mercor-extended/ots-held-out-mmmu-pro-leaderboard/) | Mercor extended-set run · high reasoning · Published margin ±4.6 · Original set 78.9% ±1.7 · 420 reported samples | MiniMax | 18.10% |

## FAQ

### What does MMMU-Pro Extended (Mercor) measure?

Answering questions that require both visual and textual understanding. This table shows Mercor-run configurations for reference and is excluded from model rankings.

### Which model leads the published MMMU-Pro Extended (Mercor) snapshot?

GPT-6.1 Sol currently leads the published MMMU-Pro Extended (Mercor) snapshot with a score of 61.30%.

### How many models are evaluated on MMMU-Pro Extended (Mercor)?

The October 15, 2026 capture contains 38 source configurations.

### Does MMMU-Pro Extended (Mercor) affect BenchLM's overall score?

Not directly. MMMU-Pro Extended (Mercor) is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.