# AIME 2025 — Mercor evaluation (AIME 2025 (Mercor))

> Solving competition math problems with integer answers. This table shows Mercor-run configurations for reference and is excluded from model rankings.

Canonical page: https://benchlm.ai/benchmarks/mercoraime2025

- Category: [Mathematics](/math)
- Last updated: October 15, 2026 capture

Evaluation results published by [Mercor](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/). Published evaluation aggregates only; task contents and dataset license grants are not included.

We captured Mercor's AIME 2025 results on October 15, 2026. The table preserves 49 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.

This dated source table is display only and does not enter overall or category rankings. Source configurations retain their external identity, including Pro descriptors and different effort settings.

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 llm-as-a-judge (lmaaj) and a judge of Gemini 3.5 Flash. Its run-count label is k = 4. The linked result page takes precedence where its setup differs, as noted above.

- [Mercor AIME 2025 results](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/)
- [Mercor APEX benchmark index](https://www.mercor.com/apex/)
- [Mercor methodology](https://www.mercor.com/apex/methodology/)
- [Upstream dataset](https://huggingface.co/datasets/MathArena/aime_2025)

## About AIME 2025 (Mercor)

- Tasks: 30 source-reported tasks
- Format: Pass@1
- Difficulty: Source-specific evaluation
- Paper: [AIME 2025 evaluation results](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-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.

AIME 2025 (Mercor) is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (49 configurations)

| Rank | Model | Configuration | Creator | Score |
|------|-------|---------------|---------|-------|
| 1 | [Opus 5](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · max reasoning · Published margin ±0 · 120 reported samples | Anthropic | 100.00% |
| 2 | [Fable 5](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · max reasoning · Published margin ±0 · 120 reported samples | Anthropic | 100.00% |
| 3 | [DeepSeek-V4-Flash](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · max reasoning · Published margin ±0 · 120 reported samples | DeepSeek | 100.00% |
| 4 | [GPT-5.5](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · xhigh reasoning · Published margin ±0 · 120 reported samples | OpenAI | 100.00% |
| 5 | [GPT-5.6 Sol (Pro)](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · max reasoning · Published margin ±0 · 120 reported samples | OpenAI | 100.00% |
| 6 | [GPT-5.6 Terra](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · max reasoning · Published margin ±0 · 120 reported samples | OpenAI | 100.00% |
| 7 | [Muse Spark 1.1](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · xhigh reasoning · Published margin ±0 · 120 reported samples | Meta | 100.00% |
| 8 | [GPT-6 Astra](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · xhigh reasoning · Published margin ±0 · 120 reported samples | OpenAI | 100.00% |
| 9 | [Fable 5.1](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · high reasoning · Published margin ±0 · 120 reported samples | Anthropic | 100.00% |
| 10 | [GPT-6 Luna](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · max reasoning · Published margin ±0 · 120 reported samples | OpenAI | 100.00% |
| 11 | [Grok 4.7](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · xhigh reasoning · Published margin ±0 · 120 reported samples | xAI | 100.00% |
| 12 | [GPT-6 Sol](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · max reasoning · Published margin ±0 · 120 reported samples | OpenAI | 100.00% |
| 13 | [Opus 5.5](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · max reasoning · Published margin ±0 · 120 reported samples | Anthropic | 100.00% |
| 14 | [Sonnet 5.5](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · max reasoning · Published margin ±0 · 120 reported samples | Anthropic | 100.00% |
| 15 | [GLM-5.3](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · max reasoning · Published margin ±0 · 120 reported samples | Zhipu | 100.00% |
| 16 | [Fable 5.1](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · max reasoning · Published margin ±0 · 120 reported samples | Anthropic | 100.00% |
| 17 | [GPT-6.1 Sol](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · max reasoning · Published margin ±0 · 120 reported samples | OpenAI | 100.00% |
| 18 | [Grok 4.6](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · xhigh reasoning · Published margin ±0 · 120 reported samples | xAI | 100.00% |
| 19 | [Muse Spark 1.3](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · xhigh reasoning · Published margin ±0 · 120 reported samples | Meta | 100.00% |
| 20 | [DeepSeek-V4-Pro-0813](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · max reasoning · Published margin ±0 · 120 reported samples | DeepSeek | 100.00% |
| 21 | [Haiku 5.5](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · max reasoning · Published margin ±0 · 120 reported samples | Anthropic | 100.00% |
| 22 | [Muse Spark 1.3](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · max reasoning · Published margin ±0 · 116 reported samples | Meta | 100.00% |
| 23 | [GPT-5.6 Luna](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · max reasoning · Published margin ±1.3 · 120 reported samples | OpenAI | 99.20% |
| 24 | [GPT-5.4](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · xhigh reasoning · Published margin ±1.3 · 120 reported samples | OpenAI | 99.20% |
| 25 | [Qwen3.8-Max](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · xhigh reasoning · Published margin ±1.3 · 119 reported samples | Alibaba | 99.20% |
| 26 | [Opus 4.8](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · max reasoning · Published margin ±2.5 · 120 reported samples | Anthropic | 98.30% |
| 27 | [Grok 4.5](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · high reasoning · Published margin ±2.5 · 120 reported samples | xAI | 98.30% |
| 28 | [DeepSeek-V4.1-Flash](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · max reasoning · Published margin ±2.1 · 120 reported samples | DeepSeek | 98.30% |
| 29 | [DeepSeek-V4-Pro](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · max reasoning · Published margin ±2.5 · 111 reported samples | DeepSeek | 98.10% |
| 30 | [Kimi K2.7 Code](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · high reasoning · Published margin ±3.3 · 109 reported samples | Kimi | 96.90% |
| 31 | [Gemini 3.1 Pro](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · high reasoning · Published margin ±5 · 120 reported samples | Google | 96.70% |
| 32 | [Kimi K2 (Thinking)](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · high reasoning · Published margin ±5 · 104 reported samples | Kimi | 96.70% |
| 33 | [GLM-5.2](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · max reasoning · Published margin ±3.7 · 112 reported samples | Zhipu | 96.70% |
| 34 | [Gemini 3.8 Flash](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · high reasoning · Published margin ±5 · 120 reported samples | Google | 96.70% |
| 35 | [Gemini 3.7 Flash](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · high reasoning · Published margin ±5 · 120 reported samples | Google | 96.70% |
| 36 | [Gemini 3.6 Flash](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · high reasoning · Published margin ±5.8 · 120 reported samples | Google | 95.80% |
| 37 | [Kimi K3](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · max reasoning · Published margin ±3.8 · 120 reported samples | Kimi | 95.80% |
| 38 | [GPT-OSS-120B](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · high reasoning · Published margin ±5.4 · 119 reported samples | OpenAI | 94.20% |
| 39 | [Opus 4.7](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · max reasoning · Published margin ±8.3 · 120 reported samples | Anthropic | 93.30% |
| 40 | [Nemotron 3 Ultra](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · high reasoning · Published margin ±8.3 · 98 reported samples | NVIDIA | 93.30% |
| 41 | [Inkling](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · high reasoning · Published margin ±7.1 · 120 reported samples | Thinking Machines | 93.30% |
| 42 | [DeepSeek-V3.2](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · Published margin ±7.9 · 120 reported samples | DeepSeek | 93.30% |
| 43 | [MiniMax-M3](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · high reasoning · Published margin ±7.9 · 118 reported samples | MiniMax | 91.70% |
| 44 | [Sonnet 4.6](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · high reasoning · Published margin ±9.2 · 120 reported samples | Anthropic | 90.00% |
| 45 | [MiniMax-M2.7](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · high reasoning · Published margin ±6.7 · 120 reported samples | MiniMax | 88.30% |
| 46 | [Sonnet 5](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · max reasoning · Published margin ±10.8 · 120 reported samples | Anthropic | 88.30% |
| 47 | [Gemma 4 31B](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · Published margin ±11.7 · 120 reported samples | Google | 84.20% |
| 48 | [Gemini 3.5 Flash](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · high reasoning · Published margin ±9.6 · 120 reported samples | Google | 81.70% |
| 49 | [Gemini 3.5 Flash Lite](https://www.mercor.com/apex/oss-benchmarks/oss-aime-2025-leaderboard/) | Single-shot agent · high reasoning · Published margin ±13.8 · 120 reported samples | Google | 70.00% |

## FAQ

### What does AIME 2025 (Mercor) measure?

Solving competition math problems with integer answers. This table shows Mercor-run configurations for reference and is excluded from model rankings.

### Which model leads the published AIME 2025 (Mercor) snapshot?

Opus 5 currently leads the published AIME 2025 (Mercor) snapshot with a score of 100.00%.

### How many models are evaluated on AIME 2025 (Mercor)?

The October 15, 2026 capture contains 49 source configurations.

### Does AIME 2025 (Mercor) affect BenchLM's overall score?

Not directly. AIME 2025 (Mercor) is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.