Benchmark
OpenAI MRCR v2 · 8-needle
Long context benchmarks measure how well models use information in long inputs. Scores are percentages. Higher is better.
- Models measured
- 28
- Scores recorded
- 74
- Sources
- 1
- IQ weight
- 1.76
Score distribution
- 78.1%
- Mean
- 84.9%
- Median
- 19.3%
- Std dev
- 44.1%
- 10th percentile
- 97.2%
- 90th percentile
- 26.3%
- Min
This benchmark has a weight of 1.76 for chat models, measured over 28 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 51 | GPT 5.5512K-1M· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 74% |
| 52 | GPT 5.5512K–1M · xhigh· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 74% |
| 53 | GPT-5.6 Sol512K-1M· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 73.8% |
| 54 | GPT-5.6 Solmax · 512K–1M · 100 examples · 8-needle · no tools · mean sequence-matcher ratio· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 73.8% |
| 55 | GPT-5.6 Terra512K-1M· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 72.5% |
| 56 | Claude Sonnet 5Gemini 3.6 Flash Model Card · July 2026 · 128K cumulative average· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 71.6% |
| 57 | Gemini 3 Flash128K cumulative average · 8-needle· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 67.2% |
| 58 | Gemini 3 FlashGemini 3.5 Flash Model Card · May 2026 · 128K cumulative average· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 67.2% |
| 59 | Gemma 4 31B ITGemma 4 Technical Report · Table 5 · thinking mode unless noted · 128K· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 66.4% |
| 60 | Muse Spark 1.2xhigh · 256K–512K · 100 examples · 8-needle · no tools · mean sequence-matcher ratio· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 66.3% |
| 61 | Gemini 3.1 Flash LiteGemini 3.1 Flash-Lite Model Card · high thinking · default sampling · single attempt/pass@1 · 128K cumulative average· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 60.1% |
| 62 | Claude Opus 4.7Gemini 3.5 Flash Model Card · May 2026 · 128K cumulative average· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 59.3% |
| 63 | GPT 5.4256K-512K· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 57.5% |
| 64 | Muse Spark 1.2xhigh · 512K–1M · 100 examples · 8-needle · no tools · mean sequence-matcher ratio· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 55.5% |
| 65 | GPT-5.4 minixhigh · 8-needle · 64K–128K· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 47.7% |
| 66 | GPT 5.4 Nanoxhigh · 8-needle · 64K–128K· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 44.2% |
| 67 | Gemma 4 26B A4BGemma 4 Technical Report · Table 5 · thinking mode unless noted · 128K· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 44.1% |
| 68 | GPT-5.6 Luna256K-512K· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 41.3% |
| 69 | GPT-5.6 Luna512K-1M· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 41.3% |
| 70 | GPT 5.4512K-1M· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 36.6% |
| 71 | GPT-5.4 minixhigh · 8-needle · 128K–256K· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 33.6% |
| 72 | GPT 5.4 Nanoxhigh · 8-needle · 128K–256K· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 33.1% |
| 73 | Step 3.5 FlashStep 3.5 technical report · Table 5 · 8-needle · vanilla· Reported by StepFun· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 28.8% |
| 74 | Step 3.5 FlashStep 3.5 technical report · Table 5 · 8-needle · PaCoRe· Reported by StepFun· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 26.3% |
Showing 51–74 of 74 results.