Model comparison
GPT-5.4 vs Mistral Large 3
Head-to-head evidence from 16 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: GPT-5.4 #8 (Supported); Mistral Large 3 #113 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. GPT-5.4 and Mistral Large 3 share 16 comparable benchmark results. 0 of 8 categories are comparable. 36 results are unique to GPT-5.4; 0 to Mistral Large 3.
Updated July 20, 2026- Shared results
- 16
- GPT-5.4 only
- 36
- Mistral Large 3 only
- 0
- Comparable categories
- 0 / 8
Benchmark data for GPT-5.4 and Mistral Large 3 is coming soon on BenchLM.
Confidence note. This is a partial-evidence comparison with 16 shared benchmark results across 6 evidence categories; 0 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
BenchLM has partial data for these models, but not enough overlapping benchmark coverage to produce a fair score-level comparison yet.
GPT-5.4 is priced at $2.50 input / $15.00 output per 1M tokens, versus $0.50 input / $1.50 output per 1M tokens for Mistral Large 3. GPT-5.4 has the larger context window at 1.05M, compared with 128K for Mistral Large 3.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
| Category | GPT-5.4 | Δ | Mistral Large 3 |
|---|---|---|---|
| Agentic | GPT-5.477.2 | MarginNo overlap | Mistral Large 3Not measured |
| Coding | GPT-5.457.7 | MarginNo overlap | Mistral Large 3Not measured |
| Knowledge | GPT-5.457.6 | MarginNo overlap | Mistral Large 3Not measured |
| Math | GPT-5.442.5 | MarginNo overlap | Mistral Large 3Not measured |
| Multimodal | GPT-5.473.2 | MarginNo overlap | Mistral Large 3Not measured |
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | GPT-5.4 | Mistral Large 3 | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | GPT-5.4$2.5 input / $15 output | Mistral Large 3$0.5 input / $1.5 output | Mistral Large 3 has the lower combined listed price. |
| Generation speedtokens per second | GPT-5.474 tok/s | Mistral Large 348 tok/s | GPT-5.4 has the higher measured throughput. |
| First-answer latencyseconds to first token | GPT-5.4151.79 s | Mistral Large 31.04 s | Mistral Large 3 reaches the first token sooner. |
| Context windowmaximum listed tokens | GPT-5.41.05M | Mistral Large 3128K | GPT-5.4 lists the larger context window. |
Benchmark Deep Dive
Agentic17 benchmarks
| Benchmark | GPT-5.4 | Mistral Large 3 | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 75.1% | — | Not comparable |
| CyberGymSource | 79.0% | — | Not comparable |
| BrowseCompSource | 82.7% | — | Not comparable |
| OSWorld-VerifiedSource | 75% | — | Not comparable |
| MCP AtlasSource | 70.6% | — | Not comparable |
| ToolathlonSource | 54.6% | — | Not comparable |
| τ²-bench resultsSource | 87.1% | 24.6% | GPT-5.4 leads |
| Claw-EvalSource | 60.3% | — | Not comparable |
| DeepSearchQASource | 73.6% | — | Not comparable |
| AA Agentic IndexSource | 41.1% | 5.5% | GPT-5.4 leads |
| APEX-Agents-AASource | 33.3% | — | Not comparable |
| GDPval-AASource | 44.7% | 6.6% | GPT-5.4 leads |
| GDPval-AASource | 1395 | 633 | GPT-5.4 leads |
| Gert LabsSource | 64.89% | — | Not comparable |
| ResearchClawBenchSource | 15.3% | — | Not comparable |
| JobBenchSource | 38.9% | — | Not comparable |
| ExploitGymSource | 6.0% | — | Not comparable |
Coding6 benchmarks
Reasoning2 benchmarks
Knowledge13 benchmarks
| Benchmark | GPT-5.4 | Mistral Large 3 | Result |
|---|---|---|---|
| GPQASource | 92.8% | — | Not comparable |
| HLESource | 52.1% | — | Not comparable |
| HLE w/o toolsSource | 39.8% | — | Not comparable |
| GPQA-DSource | 92.8% | — | Not comparable |
| HealthBench HardSource | 40.1% | — | Not comparable |
| MedXpertQA (Text)Source | 59.6% | — | Not comparable |
| Artificial Analysis Intelligence IndexSource | 51.4% | 15.9% | GPT-5.4 leads |
| AA-GPQA DiamondSource | 92.0% | 68.0% | GPT-5.4 leads |
| AA-HLESource | 41.6% | 4.1% | GPT-5.4 leads |
| AA-Omniscience IndexSource | 5.7% | -39.4% | GPT-5.4 leads |
| AA-Omniscience AccuracySource | 50.0% | 24.1% | GPT-5.4 leads |
| AA-Omniscience Hallucination RateSource | 88.6% | 83.7% | Mistral Large 3 leads |
| HealthBench ProfessionalSource | 48.1% | — | Not comparable |
Math2 benchmarks
Multimodal11 benchmarks
| Benchmark | GPT-5.4 | Mistral Large 3 | Result |
|---|---|---|---|
| MMMU-ProSource | 81.2% | — | Not comparable |
| OfficeQA ProSource | 53.2% | — | Not comparable |
| MMMU-Pro w/ PythonSource | 82.1% | — | Not comparable |
| CharXivSource | 82.8% | — | Not comparable |
| ERQASource | 65.4% | — | Not comparable |
| SimpleVQASource | 61.1% | — | Not comparable |
| ScreenSpot ProSource | 85.4% | — | Not comparable |
| ZeroBenchSource | 41.0% | — | Not comparable |
| MedXpertQA (MM)Source | 77.1% | — | Not comparable |
| AA-MMMU-ProSource | 78.4% | 55.7% | GPT-5.4 leads |
| Design Arena WebsiteSource | 1252 | — | Not comparable |
Inst. Following1 benchmarks
| Benchmark | GPT-5.4 | Mistral Large 3 | Result |
|---|---|---|---|
| AA-IFBenchSource | 73.9% | 36.2% | GPT-5.4 leads |
Frequently Asked Questions (3)
Can I compare GPT-5.4 and Mistral Large 3 on BenchLM yet?
Not fully yet. BenchLM is tracking both models, but the sourced benchmark breakdown for this comparison is still coming soon.
Why does this comparison show “coming soon”?
BenchLM only shows category winners and benchmark-level calls when we have sourced results that can be compared fairly. For these models, the public benchmark coverage is not complete enough yet.
What data is available for GPT-5.4 and Mistral Large 3 today?
GPT-5.4: $2.50 input / $15.00 output per 1M tokens Mistral Large 3: $0.50 input / $1.50 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.
Self-host vs API cost
Estimates at 50,000 req/day · 1000 tokens/req average.
Related Comparisons
Explore More
Choose a model with this week’s evidence
Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.
One email each week. Unsubscribe anytime.